Search

Your search keyword '"Technicolor"' showing total 118 results
Start Over Author "Technicolor" Topic artificial intelligence

Refine your results

118 results on '"Technicolor"'

1. Detecting Specular Reflections and Cast Shadows to Estimate Reflectance and Illumination of Dynamic Indoor Scenes

Author

Eric Marchand, Salma Jiddi, Philippe Robert, Technicolor [Cesson Sévigné], Technicolor, Geomagical Labs, InterDigital R&D France, Sensor-based and interactive robotics (RAINBOW), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-RÉALITÉ VIRTUELLE, HUMAINS VIRTUELS, INTERACTIONS ET ROBOTIQUE (IRISA-D5), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique)

Subjects
diffuse, reflectance, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Virtual reality, Metaverse, shadow, Shadow, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], specular, Computer vision, Specular reflection, mixed reality, ComputingMethodologies_COMPUTERGRAPHICS, business.industry, illumination, 020207 software engineering, Photometric registration, Computer Graphics and Computer-Aided Design, Reflectivity, Mixed reality, Range (mathematics), Specularity, Signal Processing, retexturing, RGB color model, Computer Vision and Pattern Recognition, Artificial intelligence, business, texture, Software
Abstract

International audience; The goal of Mixed Reality (MR) is to achieve a seamless and realistic blending between real and virtual worlds. This requires the estimation of reflectance properties and lighting characteristics of the real scene. One of the main challenges within this task consists in recovering such properties using a single RGB-D camera. In this paper, we introduce a novel framework to recover both the position and color of multiple light sources as well as the specular reflectance of real scene surfaces. This is achieved by detecting and incorporating information from both specular reflections and cast shadows. Our approach is capable of handling any textured surface and considers both static and dynamic light sources. Its effectiveness is demonstrated through a range of applications including visually-consistent mixed reality scenarios (e.g. correct real specularity removal, coherent shadows in terms of shape and intensity) and retexturing where the texture of the scene is altered whereas the incident lighting is preserved.

Published
2022
Full Text
View/download PDF

2. ROAM: a rich object appearance model with application to rotoscoping

Author

Juan-Manuel Perez-Rua, Patrick Bouthemy, Philip H. S. Torr, Tomas Crivelli, Patrick Pérez, Ondrej Miksik, University of Oxford, Orange Labs R&D [Rennes], France Télécom, Technicolor R & I [Cesson Sévigné], Technicolor, Space-timE RePresentation, Imaging and cellular dynamics of molecular COmplexes (SERPICO), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Structure (mathematical logic), Computer science, business.industry, Applied Mathematics, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Initialization, 02 engineering and technology, Object (computer science), Active appearance model, Computational Theory and Mathematics, Artificial Intelligence, Compositing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Computer vision, Computer Vision and Pattern Recognition, Artificial intelligence, business, ComputingMilieux_MISCELLANEOUS, Software
Abstract

Rotoscoping , the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer the artists a much better interactive control on the definition, editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given an initial closed outline of this object. This model combines a collection of local foreground/background appearance models spread along the outline, a global appearance model of the enclosed object and a set of distinctive foreground landmarks. The structure of this rich appearance model allows simple initialization, efficient iterative optimization with exact minimization at each step, and on-line adaptation in videos. We further extend this model by so-called trimaps which serve as an input to alpha-matting algorithms to allow truly seamless compositing. To this end, we leverage local classifiers attached to the roto-curves to define a confidence measure that is well-suited to define trimaps with adaptive band-widths. The resulting trimaps are parametric, temporally consistent and remain fully editable by the artist. We demonstrate qualitatively and quantitatively the merit of this framework through comparisons with tools based on either dynamic segmentation with a closed curve or pixel-wise binary labelling.

Published
2020

3. Long Short Term Memory Networks for Light Field View Synthesis

Author

Christine Guillemot, Matthieu Hog, Neus Sabater, Technicolor R & I [Cesson Sévigné], Technicolor, Analysis representation, compression and communication of visual data (Sirocco), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)

Subjects
Computer science, Plane (geometry), business.industry, Deep learning, Volume (computing), Deep Learn- ing, View Synthesis, 020207 software engineering, 02 engineering and technology, Index Terms-Light Field, View synthesis, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Logic gate, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Angular resolution, Artificial intelligence, business, Algorithm, Image resolution, ComputingMilieux_MISCELLANEOUS, Light field
Abstract

Because light field devices have a limited angular resolution, artificially reconstructing intermediate views is an interesting task. In this work, we propose a novel way to solve this problem using deep learning. In particular, the use of Long Short Term Memory Networks on a plane sweep volume is proposed. The approach has the advantage of having very few parameters and can be run on sequences with arbitrary length. We show that our approach yields results that are competitive with the state-of-the-art for dense light fields. Experimental results also show promising results with light fields with wider baselines.

Published
2019
Full Text
View/download PDF

4. Adversarial frontier stitching for remote neural network watermarking

Author

Erwan Le Merrer, Gilles Trédan, Patrick Pérez, the World Is Distributed Exploring the tension between scale and coordination (WIDE), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SYSTÈMES LARGE ÉCHELLE (IRISA-D1), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Technicolor [Cesson Sévigné], Technicolor, Équipe Tolérance aux fautes et Sûreté de Fonctionnement informatique (LAAS-TSF), Laboratoire d'analyse et d'architecture des systèmes (LAAS), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), and Université de Toulouse (UT)

Subjects
FOS: Computer and information sciences, 0209 industrial biotechnology, Computer Science - Cryptography and Security, Computer science, Neural network models, 02 engineering and technology, Watermarking, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], computer.software_genre, Model decision frontiers, Convolutional neural network, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], 020901 industrial engineering & automation, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Black box interaction, Digital watermarking, Artificial neural network, Contextual image classification, business.industry, Deep learning, Watermark, Adversarial examples, Embedding, 020201 artificial intelligence & image processing, Artificial intelligence, Data mining, business, Cryptography and Security (cs.CR), computer, Software, MNIST database
Abstract

The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress towards model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely. Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machine learning model) that is operated remotely, and available through a service API. To this end, we propose to mark the model's action itself, tweaking slightly its decision frontiers so that a set of specific queries convey the desired information. In the present paper, we formally introduce the problem and propose a novel zero-bit watermarking algorithm that makes use of adversarial model examples. While limiting the loss of performance of the protected model, this algorithm allows subsequent extraction of the watermark using only few queries. We experimented the approach on three neural networks designed for image classification, in the context of MNIST digit recognition task., To appear in the journal of Neural Computing and Applications, 2019

Published
2019
Full Text
View/download PDF

5. MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets

Author

Corentin Hardy, Erwan Le Merrer, Bruno Sericola, Technicolor R & I [Cesson Sévigné], Technicolor, Dependability Interoperability and perfOrmance aNalYsiS Of networkS (DIONYSOS), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-RÉSEAUX, TÉLÉCOMMUNICATION ET SERVICES (IRISA-D2), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), the World Is Distributed Exploring the tension between scale and coordination (WIDE), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SYSTÈMES LARGE ÉCHELLE (IRISA-D1), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique)

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial neural network, business.industry, Computer science, Group method of data handling, Node (networking), Deep learning, Machine Learning (stat.ML), 020206 networking & telecommunications, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Machine Learning (cs.LG), Domain (software engineering), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Reduction (complexity), Statistics - Machine Learning, Server, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], business, MNIST database
Abstract

A recent technical breakthrough in the domain of machine learning is the discovery and the multiple applications of Generative Adversarial Networks (GANs). Those generative models are computationally demanding, as a GAN is composed of two deep neural networks, and because it trains on large datasets. A GAN is generally trained on a single server. In this paper, we address the problem of distributing GANs so that they are able to train over datasets that are spread on multiple workers. MD-GAN is exposed as the first solution for this problem: we propose a novel learning procedure for GANs so that they fit this distributed setup. We then compare the performance of MD-GAN to an adapted version of Federated Learning to GANs, using the MNIST and CIFAR10 datasets. MD-GAN exhibits a reduction by a factor of two of the learning complexity on each worker node, while providing better performances than federated learning on both datasets. We finally discuss the practical implications of distributing GANs., Comment: To be published in IPDPS 2019: the 33rd IEEE International Parallel & Distributed Processing Symposium

Published
2019
Full Text
View/download PDF

6. Deep frame interpolation for video compression

Author

Christine Guillemot, Philippe Guillotel, Jean Begaint, Franck Galpin, Analysis representation, compression and communication of visual data (Sirocco), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Technicolor R & I [Cesson Sévigné], Technicolor, SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Motion compensation, 010308 nuclear & particles physics, business.industry, Computer science, Deep learning, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Hevc, 01 natural sciences, Video compression, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, Machine learning, Codec, Deep neural networks, Computer vision, Artificial intelligence, Motion interpolation, 010306 general physics, business, Data compression, Coding (social sciences)
Abstract

International audience; Deep neural networks have been recently proposed to solve video interpolation tasks. Given a past and future frame, such networks can be trained to successfully predict the intermediate frame(s). In the context of video compression, these architectures could be useful as an additional inter-prediction mode. Current inter-prediction methods rely on block-matching techniques to estimate the motion between consecutive frames. This approach has severe limitations for handling complex non-translational motions, and is still limited to block-based motion vectors. This paper presents a deep frame interpolation network for video compression aiming at solving the previous limitations, i.e. able to cope with all types of geometrical deformations by providing a dense motion compensation. Experiments with the classical bi-directional hierarchical video coding structure demonstrate the efficiency of the proposed approach over the traditional tools of the HEVC codec.

Published
2019
Full Text
View/download PDF

7. Towards a Perceptually-Motivated Color Space for High Dynamic Range Imaging

Author

Tania Pouli, Mekides Assefa Abebe, Mohamed-Chaker Larabi, Technicolor [Cesson Sévigné], Technicolor, Synthèse et analyse d'images (XLIM-ASALI), XLIM (XLIM), Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS), and Université de Poitiers

Subjects
Lightness, Computer science, business.industry, Dynamic range, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Colorfulness, Tone mapping, Color space, Luminance, High-dynamic-range imaging, Computer vision, Dynamic range compression, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Hue
Abstract

International audience; To reproduce the appearance of real world scenes, a number of color appearance models have been proposed thanks to adapted psycho-visual experiments. Most of them were designed and intended for a limited dynamic range, or address only dynamic range compression applications. However, given the increasing availability of displays with higher luminance and contrast ranges, a detailed analysis of appearance attributes is also necessary for dynamic range expansion scenarios. In this study, we propose a psycho-visual experimental setup, designed by adapting and combining the adjustment and partition scaling methodologies, which we employ for measuring perceptual colorfulness of color patches with different levels of lightness, chroma and hue. The proposed setup reduces the complexity and increases the efficiency relative to previous experimental setups and allows both expert and non-expert participants to be included. From the collected data, a modified color space is obtained and a new saturation model for dynamic range compression and expansion is derived for high dynamic range imaging.

Published
2017
Full Text
View/download PDF

8. Inter-Layer Prediction of Color in High Dynamic Range Image Scalable Compression

Author

Christine Guillemot, Mikael Le Pendu, Dominique Thoreau, Analysis representation, compression and communication of visual data (Sirocco ), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)

Subjects
HEVC, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Tone mapping, Color space, GeneralLiterature_MISCELLANEOUS, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Chromaticity, High dynamic range, ComputingMethodologies_COMPUTERGRAPHICS, Hue, Pixel, Dynamic range, business.industry, Color correction, Scalability, Color Correction, 030229 sport sciences, Computer Graphics and Computer-Aided Design, Color model, High Dynamic Range (HDR), Tone Mapping, 020201 artificial intelligence & image processing, Artificial intelligence, business, Software, Inter-Layer Prediction (ILP)
Abstract

International audience; This paper presents a color inter layer prediction (ILP) method for scalable coding of High Dynamic Range (HDR) video content with a Low Dynamic Range (LDR) base layer. Relying on the assumption of hue preservation between the colors of an HDR image and its LDR tone mapped version, we derived equations for predicting the chromatic components of the HDR layer given the decoded LDR layer. Two color representations are studied. In a first encoding scheme, the HDR image is represented in the classical Y'CbCr format. In addition, a second scheme is proposed using a colorspace based on the CIE u'v' uniform chromaticity scale diagram. In each case, different prediction equations are derived based on a color model ensuring the hue preservation. Our experiments highlight several advantages of using a CIE u'v' based colorspace for the compression of HDR content, especially in a scalable context. In addition, our inter-layer prediction scheme using this color representation improves on the state of the art ILP method which directly predicts the HDR layer u'v' components by computing the LDR layers u'v' values of each pixel.

Published
2016
Full Text
View/download PDF

9. Touchy : A Visual Approach for Simulating Haptic Effects on Touchscreens

Author

Antoine Costes, Ferran Argelaguet, Fabien Danieau, Philippe Guillotel, Anatole Lécuyer, Technicolor R & I [Cesson Sévigné], Technicolor, 3D interaction with virtual environments using body and mind (Hybrid), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique)

Subjects
InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.,HCI), Metaphor, Computer science, Computer Networks and Communications, pseudo-haptics, media_common.quotation_subject, friction, perception, 01 natural sciences, lcsh:QA75.5-76.95, law.invention, 03 medical and health sciences, InformationSystems_MODELSANDPRINCIPLES, 0302 clinical medicine, Touchscreen, Visual approach, law, Human–computer interaction, Artificial Intelligence, Perception, 0103 physical sciences, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Macro, 010306 general physics, ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS, Haptic technology, media_common, roughness, Cursor (user interface), hardness, Hardware and Architecture, lcsh:Electronic computers. Computer science, touchscreen, Actuator, 030217 neurology & neurosurgery, Software, Information Systems
Abstract

Haptic enhancement of touchscreens usually involves vibrating motors producing limited sensations or custom mechanical actuators that are difficult to disseminate. In this paper, we propose an alternative approach called “Touchy,” where a symbolic cursor is introduced under the user's finger, to evoke various haptic properties through changes in its shape and motion. This novel metaphor enables to address four different perceptual dimensions, namely: hardness, friction, fine roughness, and macro roughness. Our metaphor comes with a set of seven visual effects that we compared with real texture samples within a user study conducted with 14 participants. Taken together our results show that Touchy is able to elicit clear and distinct haptic properties: stiffness, roughness, reliefs, stickiness, and slipperiness.

Published
2019
Full Text
View/download PDF

10. SoDeep: a Sorting Deep net to learn ranking loss surrogates

Author

Matthieu Cord, Patrick Pérez, Louis Chevallier, Martin Engilberge, Engilberge, Martin, Technicolor R & I [Cesson Sévigné], Technicolor, Machine Learning and Information Access (MLIA), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), InterDigital Communications, Valeo.ai, and VALEO

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Machine Learning (stat.ML), 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], 010501 environmental sciences, [INFO] Computer Science [cs], Machine learning, computer.software_genre, 01 natural sciences, Synthetic data, Computer Science - Information Retrieval, Machine Learning (cs.LG), Ranking (information retrieval), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], Proxy (statistics), 0105 earth and related environmental sciences, Flexibility (engineering), Contextual image classification, business.industry, Deep learning, Sorting, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Metric (mathematics), 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Information Retrieval (cs.IR)
Abstract

Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be specific to a given metric. In the present work, we introduce a new method to learn approximations of such non-differentiable objective functions. Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores. It is trained virtually for free using synthetic data. This sorting deep (SoDeep) net can then be combined in a plug-and-play manner with existing deep architectures. We demonstrate the interest of our approach in three different tasks that require ranking: Cross-modal text-image retrieval, multi-label image classification and visual memorability ranking. Our approach yields very competitive results on these three tasks, which validates the merit and the flexibility of SoDeep as a proxy for sorting operation in ranking-based losses., Comment: Accepted to CVPR 2019

Published
2019

11. Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision

Author

Patrick Pérez, Gael Richard, Alexey Ozerov, Ngoc Q. K. Duong, Sanjeel Parekh, Slim Essid, Technicolor R & I [Cesson Sévigné], Technicolor, Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Valeo.ai, and VALEO

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Matrix decomposition, Non-negative matrix factorization, audio-visual event detection, non-negative matrix factorization, 030507 speech-language pathology & audiology, 03 medical and health sciences, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Audio visual, 0202 electrical engineering, electronic engineering, information engineering, Source separation, Computer vision, Neural and Evolutionary Computing (cs.NE), [SPI.ACOU]Engineering Sciences [physics]/Acoustics [physics.class-ph], Scene analysis, Modality (human–computer interaction), business.industry, Computer Science - Neural and Evolutionary Computing, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Object (computer science), multiple instance learning, Index Terms-Audio-visual event detection, source separation, 020201 artificial intelligence & image processing, Artificial intelligence, 0305 other medical science, business, Feature learning
Abstract

We tackle the problem of audio-visual scene analysis for weakly-labeled data. To this end, we build upon our previous audio-visual representation learning framework to perform object classification in noisy acoustic environments and integrate audio source enhancement capability. This is made possible by a novel use of non-negative matrix factorization for the audio modality. Our approach is founded on the multiple instance learning paradigm. Its effectiveness is established through experiments over a challenging dataset of music instrument performance videos. We also show encouraging visual object localization results.

Published
2018

12. KinesTouch: 3D Force-Feedback Rendering for Tactile Surfaces

Author

Fabien Danieau, Ferran Argelaguet-Sanz, Philippe Guillotel, Anatole Lécuyer, Antoine Costes, Technicolor R & I [Cesson Sévigné], Technicolor, 3D interaction with virtual environments using body and mind (Hybrid), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique)

Subjects
Computer science, business.industry, InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.,HCI), 05 social sciences, 020207 software engineering, 02 engineering and technology, [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Rendering (computer graphics), law.invention, Touchscreen, law, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, Computer vision, Artificial intelligence, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], business, Sensory cue, 050107 human factors, Haptic technology
Abstract

International audience; In this paper, we introduce the KinesTouch, a novel approach for tactile screen enhancement providing four types of haptic feedback with a single force-feedback device: compliance, friction, fine roughness, and shape. We present the design and implementation of a corresponding set of haptic effects as well as a proof-of-concept setup. Regarding friction in particular, we propose a novel effect based on large lateral motion that increases or diminishes the sliding velocity between the finger and the screen. A user study was conducted on this effect to confirm its ability to produce distinct sliding sensations. Visual cues were confirmed to influence sliding judgments, but further studies would help clarifying the role of tactile cues. Finally, we showcase several use cases illustrating the possibilities offered by the KinesTouch to enhance 2D and 3D interactions on tactile screens in various contexts.

Published
2018
Full Text
View/download PDF

13. Probeless and Realistic Mixed Reality Application in Presence of Dynamic Light Sources

Author

Anthony Laurent, Salma Jiddi, Eric Marchand, Pierrick Jouet, Caroline Baillard, Matthieu Fradet, Philippe Hobert, Technicolor [Cesson Sévigné], Technicolor, Sensor-based and interactive robotics (RAINBOW), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1)

Subjects
Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Reflectance, Virtual reality, Metaverse, Photometry, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, [INFO]Computer Science [cs], Specular reflection, Lighting, ComputingMethodologies_COMPUTERGRAPHICS, Scene analysis, business.industry, Modeling, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Textures, Scene Analysis, Reflectivity, Mixed reality, Mixed Reality, RGB color model, 020201 artificial intelligence & image processing, Augmented reality, Artificial intelligence, business, Shadows
Abstract

International audience; In this work, we consider the challenge of achieving a coherent blending between real and virtual worlds in the context of a Mixed Reality (MR) scenario. Specifically, we have designed and implemented an interactive demonstrator that shows a realistic MR application without using any light probe. The proposed system takes as input the RGB stream of the real scene, and uses these data to recover both the position and intensity of light sources. The lighting can be static and/or dynamic and the geometry of the scene can be partially altered. Our system is robust in presence of specular effects and handles both uniform and/or textured surfaces.

Published
2018

14. Annotating, Understanding, and Predicting Long-term Video Memorability

Author

Claire-Hélène Demarty, Romain Cohendet, Karthik Yadati, Ngoc Q. K. Duong, Institut de Recherche en Communications et en Cybernétique de Nantes (IRCCyN), Mines Nantes (Mines Nantes)-École Centrale de Nantes (ECN)-Ecole Polytechnique de l'Université de Nantes (EPUN), Université de Nantes (UN)-Université de Nantes (UN)-PRES Université Nantes Angers Le Mans (UNAM)-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], and Technicolor

Subjects
Computer science, Scene understanding, [SCCO.COMP]Cognitive science/Computer science, 02 engineering and technology, Machine learning, computer.software_genre, Semantics, 050105 experimental psychology, Memorization, Long-term memory, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, Global video features, Measurement protocol, Protocol (object-oriented programming), business.industry, 05 social sciences, Video memorability, Memory retention, Visualization, Term (time), [SCCO.PSYC]Cognitive science/Psychology, 020201 artificial intelligence & image processing, Artificial intelligence, Metric (unit), Attributes, business, computer
Abstract

International audience; Memorability can be regarded as a useful metric of video importance to help make a choice between competing videos. Research on computational understanding of video memorability is however in its early stages. There is no available dataset for modelling purposes, and the few previous attempts provided protocols to collect video memorability data that would be difficult to generalize. Furthermore, the computational features needed to build a robust memorability predictor remain largely undiscovered. In this article, we propose a new protocol to collect long-term video memorability annotations. We measure the memory performances of 104 participants from weeks to years after memorization to build a dataset of 660 videos for video memorability prediction. This dataset is made available for the research community. We then analyze the collected data in order to better understand video memorability, in particular the effects of response time, duration of memory retention and repetition of visualization on video memorability. We finally investigate the use of various types of audio and visual features and build a computational model for video memorability prediction. We conclude that high level visual semantics help better predict the memorability of videos.

Published
2018
Full Text
View/download PDF

15. Image Selection in Photo Albums

Author

Jonathan Kervec, Dmitry Kuzovkin, Tania Pouli, Olivier Le Meur, Rémi Cozot, Kadi Bouatouch, Technicolor R & I [Cesson Sévigné], Technicolor, Computational Visual Perception and Applications ( PERCEPT), MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Computational Visual Perception and Applications (PERCEPT), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes)

Subjects
Image quality, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), 02 engineering and technology, Task (project management), 0202 electrical engineering, electronic engineering, information engineering, Selection (linguistics), 0501 psychology and cognitive sciences, Adaptation (computer science), 050107 human factors, Information retrieval, Image selection, business.industry, Deep learning, 05 social sciences, Image aesthetics, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Photo selection, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Assessment methods, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; The selection of the best photos in personal albums is a task that is often faced by photographers. This task can become laborious when the photo collection is large and it contains multiple similar photos. Recent advances on image aesthetics and photo importance evaluation has led to the creation of different metrics for automatically assessing a given image. However, these metrics are intended for the independent assessment of an image, without considering the possible context implicitly present within photo albums. In this work, we perform a user study for assessing how users select photos when provided with a complete photo album---a task that better reflects how users may review their personal photos and collections. Using the data provided by our study, we evaluate how existing state-of-the-art photo assessment methods perform relative to user selection, focusing in particular on deep learning based approaches. Finally, we explore a recent framework for adapting independent image scores to collections and evaluate in which scenarios such an adaptation can prove beneficial.

Published
2018
Full Text
View/download PDF

16. Region-based models for motion compensation in video compression

Author

Philippe Guillotel, Franck Galpin, Jean Begaint, Christine Guillemot, Technicolor R & I [Cesson Sévigné], Technicolor, Analysis representation, compression and communication of visual data ( Sirocco ), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE ( IRISA_D5 ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), Analysis representation, compression and communication of visual data (Sirocco), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1)

Subjects
Motion compensation, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Aspect ratio (image), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Multimedia, 0202 electrical engineering, electronic engineering, information engineering, Codec, 020201 artificial intelligence & image processing, Computer vision, Affine transformation, Artificial intelligence, Zoom, business, Geometric modeling, Homography (computer vision), Data compression, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

International audience; Video codecs are primarily designed assuming that rigid, block-based, two-dimensional displacements are suitable models to describe the motion taking place in a scene. However, translational models are not sufficient to handle real world motion types such as camera zoom, shake, pan, shearing or changes in aspect ratio. We present here a region-based inter-prediction scheme to compensate such motion. The proposed mode is able to estimate multiple homography models in order to predict complex scene motion. We also introduce an affine photometric correction to each geometric model. Experiments on targeted sequences with complex motion demonstrate the efficiency of the proposed approach compared to the state-of-the-art HEVC video codec.

Published
2018
Full Text
View/download PDF

17. Light Field Inpainting Propagation via Low Rank Matrix Completion

Author

Christine Guillemot, Mikael Le Pendu, Xiaoran Jiang, Technicolor R & I [Cesson Sévigné], Technicolor, Département Electronique (ELEC), Université européenne de Bretagne - European University of Brittany (UEB)-Télécom Bretagne-Institut Mines-Télécom [Paris] (IMT), Analysis representation, compression and communication of visual data (Sirocco), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), This project has been supported in part by the EU H2020 Research and Innovation Programme under grant agreement No 694122 (ERC advanced grant CLIM) and in part by a Google faculty research award., European Project: ERC-2016-STG-694122,CLIM, Université européenne de Bretagne - European University of Brittany (UEB)-Institut Mines-Télécom [Paris] (IMT)-Télécom Bretagne, SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1)

Subjects
Matrix completion, business.industry, Computer science, Inpainting, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020206 networking & telecommunications, Low-rank approximation, 02 engineering and technology, Computer Graphics and Computer-Aided Design, Matrix decomposition, Light Field, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Computer Vision and Pattern Recognition, homography, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Segmentation, Low rank matrix completion, Artificial intelligence, business, Software, Light field
Abstract

International audience; Building up on the advances in low rank matrix completion, this article presents a novel method for propagating the inpainting of the central view of a light field to all the other views. After generating a set of warped versions of the inpainted central view with random homographies, both the original light field views and the warped ones are vectorized and concatenated into a matrix. Because of the redundancy between the views, the matrix satisfies a low rank assumption enabling us to fill the region to inpaint with low rank matrix completion. To this end, a new matrix completion algorithm, better suited to the inpainting application than existing methods, is also developed in this paper. In its simple form, our method does not require any depth prior, unlike most existing light field inpainting algorithms. The method has then been extended to better handle the case where the area to inpaint contains depth discontinuities. In this case, a segmentation map of the different depth layers of the inpainted central view is required. This information is used to warp the depth layers with different homographies. Our experiments with natural light fields captured with plenoptic cameras demonstrate the robustness of the low rank approach to noisy data as well as large color and illumination variations between the views of the light field.

Published
2018
Full Text
View/download PDF

18. Towards an automatic correction of over-exposure in photographs: Application to tone-mapping

Author

Tania Pouli, Mekides Assefa Abebe, Alexandra Booth, Jonathan Kervec, Mohamed-Chaker Larabi, Synthèse et analyse d'images (XLIM-ASALI), XLIM (XLIM), Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS), Université de Poitiers, Technicolor [Cesson Sévigné], and Technicolor

Subjects
Computer science, High dynamic range imaging, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Tone mapping, Luminance, White point, Clipping (photography), High-dynamic-range imaging, 0202 electrical engineering, electronic engineering, information engineering, Specular highlight, Preprocessor, Computer vision, business.industry, 020207 software engineering, Over-exposure correction, Tone-Mapping, Signal Processing, Image enhancement, RGB color model, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Software
Abstract

International audience; A common artifact in photographs is over-exposure due to bright scene features exceeding the abilities of the camera, and causing image areas to appear flat and lacking in detail. Although a wider luminance range could be captured with HDR techniques, this is often not possible, especially in moving scenes. To address this issue, we propose a novel solution for recovering lost details in clipped and over-exposed areas by taking advantage of channel cross-correlation in RGB images. To automate our approach we propose two improvements: 1) using the image white point, we adaptively estimate a clipping threshold value per image, and 2) to better understand the forms of over-exposure, for an optimal selection of parameters, we construct an image database focusing on over-exposed areas and automatically classify over-exposure as light sources, specular highlights or diffuse surfaces. We evaluate our solution using objective metrics and a subjective study based on an ITU standard protocol, showing that our correction leads to improved results compared to previous related techniques. We explore several potential applications of our method, including extending to video as well as using it as a preprocessing step prior to reverse tone mapping.

Published
2018
Full Text
View/download PDF

19. Inter-prediction methods based on linear embedding for video compression

Author

Dominique Thoreau, Christine Guillemot, Philippe Guillotel, Martin Alain, Analysis representation, compression and communication of visual data (Sirocco ), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)

Subjects
Temporal prediction, business.industry, Pattern recognition, Locally linear embedding, k-nearest neighbors algorithm, Video compression, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Prediction methods, Signal Processing, Codec, Computer Vision and Pattern Recognition, Artificial intelligence, Electrical and Electronic Engineering, business, Linear combination, Linear embedding, Software, Reference frame, Mathematics, Coding (social sciences), Data compression
Abstract

This paper considers the problem of temporal prediction for inter-frame coding of video sequences using locally linear embedding (LLE). LLE-based prediction, first considered for intra-frame prediction, computes the predictor as a linear combination of K nearest neighbors (K-NN) searched within one or several reference frames. The paper explores different K-NN search strategies in the context of temporal prediction, leading to several temporal predictor variants. The proposed methods are tested as extra inter-frame prediction modes in an H.264 codec, but the proposed concepts are still valid in HEVC. The results show that significant rate-distortion performance gains are obtained with respect to H.264 (up to 15.31% bit-rate saving). HighlightsNew inter-frame prediction methods based on locally linear embedding are introduced.The proposed methods are implemented in H.264, but the concepts are still valid in HEVC.The proposed methods outperform H.264 in terms of RD performances.Combining the proposed methods for intra- and inter-prediction improves the performances.

Published
2015
Full Text
View/download PDF

20. AUDASCITY: AUdio Denoising by Adaptive Social CosparsITY

Author

Clément Gaultier, Rémi Gribonval, Nancy Bertin, Srdan Kitic, Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio (PANAMA), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Technicolor [Cesson Sévigné], Technicolor, European Project: 277906,EC:FP7:ERC,ERC-2011-StG_20101014,PLEASE(2012), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Denoising, Audio signal, Noise measurement, Computer science, business.industry, Noise reduction, Speech recognition, 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, White noise, 030507 speech-language pathology & audiology, 03 medical and health sciences, Signal-to-noise ratio, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Sound, Audio, Social Cosparsity, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 0202 electrical engineering, electronic engineering, information engineering, Video denoising, Artificial intelligence, 0305 other medical science, business, Block (data storage)
Abstract

International audience; This work aims at introducing a new algorithm, AUDASCITY, and comparing its performance to the time-frequency block thresholding algorithm for the ill-posed problem of audio denoising. We propose a heuristics which combines time-frequency structure, cosparsity, and an adaptive scheme to denoise audio signals corrupted with white noise. We report that AUDASCITY outperforms state-of-the-art for each numerical comparison. While there is still room for some perceptual improvements, AUDASCITY's usefulness is shown when used as a front-end for a classification task.

Published
2018
Full Text
View/download PDF

21. Learning a Complete Image Indexing Pipeline

Author

Rémi Gribonval, Himalaya Jain, Patrick Pérez, Joaquin Zepeda, Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio ( PANAMA ), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE ( IRISA_D5 ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), Technicolor R & I [Cesson Sévigné], Technicolor, Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio (PANAMA), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Amazon, Seattle, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)

Subjects
FOS: Computer and information sciences, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, business.industry, Computer science, Computer Vision and Pattern Recognition (cs.CV), Deep learning, Search engine indexing, Computer Science - Computer Vision and Pattern Recognition, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, 02 engineering and technology, computer.software_genre, Inverted index, Pipeline (software), Image (mathematics), Index (publishing), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Data mining, Artificial intelligence, business, computer
Abstract

International audience; To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance computation mechanism to rapidly scan these lists. While supervised deep learning has recently enabled improvements to the latter, the former continues to be based on unsupervised clustering in the literature. In this work, we propose a first system that learns both components within a unifying neural framework of structured binary encoding.

Published
2018

22. Region-based prediction for image compression in the cloud

Author

Dominique Thoreau, Philippe Guillotel, Jean Begaint, Christine Guillemot, Technicolor R & I [Cesson Sévigné], Technicolor, Analysis representation, compression and communication of visual data (Sirocco), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Analysis representation, compression and communication of visual data ( Sirocco ), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE ( IRISA_D5 ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1)

Subjects
0209 industrial biotechnology, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, Cloud computing, 02 engineering and technology, Image segmentation, Computer Graphics and Computer-Aided Design, 020901 industrial engineering & automation, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Cloud storage, Software, Transform coding, Image compression
Abstract

Thanks to the increasing number of images stored in the cloud, external image similarities can be leveraged to efficiently compress images by exploiting inter-images correlations. In this paper, we propose a novel image prediction scheme for cloud storage. Unlike current state-of-the-art methods, we use a semi-local approach to exploit inter-image correlation. The reference image is first segmented into multiple planar regions determined from matched local features and super-pixels. The geometric and photometric disparities between the matched regions of the reference image and the current image are then compensated. Finally, multiple references are generated from the estimated compensation models and organized in a pseudo-sequence to differentially encode the input image using classical video coding tools. Experimental results demonstrate that the proposed approach yields significant rate-distortion performance improvements compared with the current image inter-coding solutions such as high efficiency video coding.

Published
2018
Full Text
View/download PDF

23. Video Style Transfer by Consistent Adaptive Patch Sampling

Author

Oriel Frigo, Julie Delon, Pierre Hellier, Neus Sabater, Mathématiques Appliquées Paris 5 (MAP5 - UMR 8145), Université Paris Descartes - Paris 5 (UPD5)-Institut National des Sciences Mathématiques et de leurs Interactions (INSMI)-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, MAP5 - Mathématiques Appliquées à Paris 5 (MAP5), Centre National de la Recherche Scientifique (CNRS) - Institut National des Sciences Mathématiques et de leurs Interactions - Université Paris Descartes - Paris 5 (UPD5), Mathématiques Appliquées à Paris 5 ( MAP5 - UMR 8145 ), and Université Paris Descartes - Paris 5 ( UPD5 ) -Institut National des Sciences Mathématiques et de leurs Interactions-Centre National de la Recherche Scientifique ( CNRS )

Subjects
Computer science, Computation, 02 engineering and technology, computer.software_genre, Style (sociolinguistics), Image (mathematics), Style transfer, Computer graphics, [INFO.INFO-TI] Computer Science [cs]/Image Processing, Transfer (computing), [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, Markov Random Fields, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Multimedia, Artificial neural network, business.industry, Sampling (statistics), 020207 software engineering, Texture synthesis, Computer Graphics and Computer-Aided Design, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, computer, Software
Abstract

International audience; This paper addresses the example-based stylization of videos. Style transfer aims at editing an image so that it matches the style of an example. This topic has recently been investigated massively, both in the industry and academia. The difficulty lies in how to capture the style of an image. For this work we build on our previous work " Split and Match " for still pictures, based on adaptive patch synthesis. We address the issue of extending that particular technique to video, ensuring that the solution is spatially and temporally consistent. Results show that our video style transfer is visually plausible, while being very competitive regarding computation time and memory when compared to neural network approaches.

Published
2018
Full Text
View/download PDF

24. Directing Cinematographic Drones

Author

Julien Fleureau, Quentin Galvane, Marc Christie, Philippe Guillotel, Christophe Lino, Fabien Servant, Francois-Louis Tariolle, Technicolor R & I [Cesson Sévigné], Technicolor, Analysis-Synthesis Approach for Virtual Human Simulation (MIMETIC), Université de Rennes 2 (UR2), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes 2 (UR2)-Inria Rennes – Bretagne Atlantique, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique)

Subjects
FOS: Computer and information sciences, 0209 industrial biotechnology, Computer science, animation, •Computing methodologies → Multi-agent planning, 02 engineering and technology, cinematography, Computer Science - Robotics, 020901 industrial engineering & automation, drones, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Motion planning, interactive con- trol Concepts: •Human-centered computing → User centered de- sign, business.industry, 020207 software engineering, Animation, Computer Graphics and Computer-Aided Design, Drone, [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Cinematography, Motion path planning, Artificial intelligence, •Applied computing → Media arts, business, Robotics (cs.RO)
Abstract

Quadrotor drones equipped with high-quality cameras have rapidly raised as novel, cheap, and stable devices for filmmakers. While professional drone pilots can create aesthetically pleasing videos in short time, the smooth—and cinematographic—control of a camera drone remains challenging for most users, despite recent tools that either automate part of the process or enable the manual design of waypoints to create drone trajectories. This article moves a step further by offering high-level control of cinematographic drones for the specific task of framing dynamic targets. We propose techniques to automatically and interactively plan quadrotor drone motions in dynamic three-dimensional (3D) environments while satisfying both cinematographic and physical quadrotor constraints. We first propose the Drone Toric Space , a dedicated camera parameter space with embedded constraints, and derive some intuitive on-screen viewpoint manipulators. Second, we propose a dedicated path planning technique that ensures both that cinematographic properties can be enforced along the path and that the path is physically feasible by a quadrotor drone. At last, we build on the Drone Toric Space and the specific path planning technique to coordinate the motion of multiple drones around dynamic targets. A number of results demonstrate the interactive and automated capacities of our approaches on different use-cases.

Published
2017
Full Text
View/download PDF

25. Distributed deep learning on edge-devices: feasibility via adaptive compression

Author

Erwan Le Merrer, Bruno Sericola, Corentin Hardy, Technicolor R & I [Cesson Sévigné], Technicolor, Dependability Interoperability and perfOrmance aNalYsiS Of networkS (DIONYSOS), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-RÉSEAUX, TÉLÉCOMMUNICATION ET SERVICES (IRISA-D2), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique)

Subjects
FOS: Computer and information sciences, Edge device, Active learning (machine learning), Computer science, Real-time computing, 02 engineering and technology, 010501 environmental sciences, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], 01 natural sciences, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Server, 0202 electrical engineering, electronic engineering, information engineering, 0105 earth and related environmental sciences, business.industry, Deep learning, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], Online machine learning, 020206 networking & telecommunications, Computer Science - Learning, Stochastic gradient descent, Asynchronous communication, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Embedding, Artificial intelligence, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], business, MNIST database
Abstract

A large portion of data mining and analytic services use modern machine learning techniques, such as deep learning. The state-of-the-art results by deep learning come at the price of an intensive use of computing resources. The leading frameworks (e.g., TensorFlow) are executed on GPUs or on high-end servers in datacenters. On the other end, there is a proliferation of personal devices with possibly free CPU cycles; this can enable services to run in users' homes, embedding machine learning operations. In this paper, we ask the following question: Is distributed deep learning computation on WAN connected devices feasible, in spite of the traffic caused by learning tasks? We show that such a setup rises some important challenges, most notably the ingress traffic that the servers hosting the up-to-date model have to sustain. In order to reduce this stress, we propose adaComp, a novel algorithm for compressing worker updates to the model on the server. Applicable to stochastic gradient descent based approaches, it combines efficient gradient selection and learning rate modulation. We then experiment and measure the impact of compression, device heterogeneity and reliability on the accuracy of learned models, with an emulator platform that embeds TensorFlow into Linux containers. We report a reduction of the total amount of data sent by workers to the server by two order of magnitude (e.g., 191-fold reduction for a convolutional network on the MNIST dataset), when compared to a standard asynchronous stochastic gradient descent, while preserving model accuracy., Best paper award at IEEE International Symposium on Network Computing and Applications (NCA 2017)

Published
2017

26. SUBIC: A supervised, structured binary code for image search

Author

Rémi Gribonval, Joaquin Zepeda, Himalaya Jain, Patrick Pérez, Technicolor R & I [Cesson Sévigné], Technicolor, Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio (PANAMA), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Hash function, Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, 01 natural sciences, Convolutional neural network, 010104 statistics & probability, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Entropy (information theory), 0101 mathematics, Entropy (energy dispersal), Image retrieval, Artificial neural network, business.industry, Deep learning, Quantization (signal processing), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Visualization, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], 020201 artificial intelligence & image processing, Binary code, Artificial intelligence, business
Abstract

For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and novel architectures ushered in by the deep learning revolution. We hence propose herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search. Our method makes use of a novel block-softmax non-linearity and of batch-based entropy losses that together induce structure in the learned encodings. We show that our method outperforms state-of-the-art compact representations based on deep hashing or structured quantization in single and cross-domain category retrieval, instance retrieval and classification. We make our code and models publicly available online., Accepted at ICCV 2017 (Spotlight)

Published
2017
Full Text
View/download PDF

27. Scalable Light Field Compression Scheme Using Sparse Reconstruction and Restoration

Author

Guillaume Boisson, Christine Guillemot, Fatma Hawary, Dominique Thoreau, Technicolor R & I [Cesson Sévigné], Technicolor, Analysis representation, compression and communication of visual data (Sirocco), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Analysis representation, compression and communication of visual data ( Sirocco ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE ( IRISA_D5 ), Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Université de Rennes 1 ( UR1 ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ) -Institut de Recherche en Informatique et Systèmes Aléatoires ( IRISA ), Université de Rennes ( UNIV-RENNES ) -Université de Rennes ( UNIV-RENNES ) -Institut National des Sciences Appliquées - Rennes ( INSA Rennes ) -Université de Bretagne Sud ( UBS ) -École normale supérieure - Rennes ( ENS Rennes ) -CentraleSupélec-Centre National de la Recherche Scientifique ( CNRS ) -IMT Atlantique Bretagne-Pays de la Loire ( IMT Atlantique ), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
HEVC, [ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing, Data_CODINGANDINFORMATIONTHEORY, 02 engineering and technology, Iterative reconstruction, symbols.namesake, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Compression (functional analysis), Encoding (memory), 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Light field, Image restoration, Mathematics, business.industry, sparsity, 020206 networking & telecommunications, computer.file_format, compression, Fourier transform, SHVC, symbols, 020201 artificial intelligence & image processing, Artificial intelligence, Bit Rate Reduction, business, computer, Decoding methods
Abstract

International audience; This paper describes a light field scalable compression scheme based on the sparsity of the angular Fourier transform of the light field. A subset of sub-aperture images (or views) is compressed using HEVC as a base layer and transmitted to the decoder. An entire light field is reconstructed from this view subset using a method exploiting the sparsity of the light field in the continuous Fourier domain. The reconstructed light field is enhanced using a patch-based restoration method. Then, restored samples are used to predict original ones, in a SHVC-based SNR-scalable scheme. Experiments with different datasets show a significant bit rate reduction of up to 24% in favor of the proposed compression method compared with a direct encoding of all the views with HEVC. The impact of the compression on the quality of the all-in-focus images is also analyzed showing the advantage of the proposed scheme.

Published
2017

28. Perceptual Lightness Modeling for High-Dynamic-Range Imaging

Author

Erik Reinhard, Mekides Assefa Abebe, Mohamed-Chaker Larabi, Tania Pouli, Technicolor [Cesson Sévigné], Technicolor, Université de Poitiers, Synthèse et analyse d'images (XLIM-ASALI), XLIM (XLIM), and Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Lightness, General Computer Science, Dynamic range, business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Experimental and Cognitive Psychology, 02 engineering and technology, Color space, Luminance, Theoretical Computer Science, Range (mathematics), High-dynamic-range imaging, Human visual system model, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, High dynamic range, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

International audience; The human visual system (HVS) non-linearly processes light from the real world, allowing us to perceive detail over a wide range of illumination. Although models that describe this non-linearity are constructed based on psycho-visual experiments, they generally apply to a limited range of illumination and therefore may not fully explain the behavior of the HVS under more extreme illumination conditions. We propose a novel experimental protocol for measuring visual response to stimuli which does not require participant training, nor does it require the participants to be experts. Furthermore, the protocol can be applied to stimuli covering an extended luminance range. We argue that this protocol may be equally useful for measuring visual response in different perceptual dimensions, such as hue and chroma. Based on the outcome of our experiment, we propose a new model describing lightness response over an extended luminance range. The model can be integrated with existing color appearance models or perceptual color spaces. To demonstrate the eectiveness of our model in high dynamic range (HDR) applications, we evaluate its suitability for dynamic range expansion relative to existing solutions.

Published
2017
Full Text
View/download PDF

29. Kernel Square-Loss Exemplar Machines for Image Retrieval

Author

Patrick Pérez, Jean Ponce, Joaquin Zepeda, Francis Bach, Rafael Sampaio de Rezende, Models of visual object recognition and scene understanding (WILLOW), Département d'informatique de l'École normale supérieure (DI-ENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), Technicolor R & I [Cesson Sévigné], Technicolor, Amazon, Laboratoire d'informatique de l'école normale supérieure (LIENS), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Statistical Machine Learning and Parsimony (SIERRA), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Département d'informatique - ENS Paris (DI-ENS), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Département d'informatique - ENS Paris (DI-ENS), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Recherche d'image, Computational complexity theory, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, Matrix decomposition, Kernel Methods, Hinge loss, 0202 electrical engineering, electronic engineering, information engineering, Image retrieval, 0105 earth and related environmental sciences, Mathematics, Image Search, Example-based, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Support vector machine, Kernel method, Kernel (image processing), Méthode à noyaux, 020201 artificial intelligence & image processing, Artificial intelligence, business, Encoder
Abstract

International audience; Zepeda and Pérez have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval. This paper extends this approach in several directions: We first show that replacing the hinge loss by the square loss in the ESVM cost function significantly reduces encoding time with negligible effect on accuracy. We call this model square-loss exemplar machine, or SLEM. We then introduce a kernelized SLEM which can be implemented efficiently through low-rank matrix decomposition , and displays improved performance. Both SLEM variants exploit the fact that the negative examples are fixed, so most of the SLEM computational complexity is relegated to an offline process independent of the positive examples. Our experiments establish the performance and computational advantages of our approach using a large array of base features and standard image retrieval datasets.

Published
2017
Full Text
View/download PDF

30. Scalable Image Coding based on Epitomes

Author

Philippe Guillotel, Christine Guillemot, Dominique Thoreau, Martin Alain, Analysis representation, compression and communication of visual data (Sirocco), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Technicolor R & I [Cesson Sévigné], Technicolor, SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
FOS: Computer and information sciences, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, super-resolution, 02 engineering and technology, Iterative reconstruction, Epitome, 0202 electrical engineering, electronic engineering, information engineering, Layer (object-oriented design), Image restoration, Pixel, business.industry, 020206 networking & telecommunications, Pattern recognition, Computer Graphics and Computer-Aided Design, SHVC, scalable image coding, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Scalability, 020201 artificial intelligence & image processing, Artificial intelligence, business, Software
Abstract

In this paper, we propose a novel scheme for scalable image coding based on the concept of epitome. An epitome can be seen as a factorized representation of an image. Focusing on spatial scalability, the enhancement layer of the proposed scheme contains only the epitome of the input image. The pixels of the enhancement layer not contained in the epitome are then restored using two approaches inspired from local learning-based super-resolution methods. In the first method, a locally linear embedding model is learned on base layer patches and then applied to the corresponding epitome patches to reconstruct the enhancement layer. The second approach learns linear mappings between pairs of co-located base layer and epitome patches. Experiments have shown that significant improvement of the rate-distortion performances can be achieved compared to an SHVC reference., Preprint submitted to IEEE Trans. on Image Processing

Published
2017
Full Text
View/download PDF

31. Which saliency weighting for omni directional image quality assessment?

Author

Yashas Rai, Philippe Guillotel, Patrick Le Callet, Laboratoire des Sciences du Numérique de Nantes (LS2N), Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Image Perception Interaction (IPI), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Technicolor R & I [Cesson Sévigné], Technicolor, IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Viewport, business.industry, Computer science, Image quality, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, 02 engineering and technology, Virtual reality, Gaze, Rendering (computer graphics), Visualization, Weighting, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, Eye tracking, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, ComputingMilieux_MISCELLANEOUS
Abstract

With the explosion of Virtual Reality technologies, the production and usage of omni directional images (a.k.a 360 images) is presenting new challenges in the domains of compression, transmission and rendering. The evaluation of the quality of images generated by these technologies is therefore paramount. As the exploration of 360 images within a Head-Mounted Display (HMD) is non-uniform, current state of the art proposes a saliency weighting of distortions (between a reference and an impaired version) thus allowing us to highlight impairments in frequently attended regions. So far, saliency maps have been generated by tracking head motion alone, and consider that the view-port orientation alone is sufficient to determine saliency. The added value of eye gaze tracking within the viewport has not been studied in this domain yet. In this work, an eye-tracking experiment is performed using a HMD and is followed by subsequent gaze analysis to appreciate the visual attention behavior within a view-port. Results suggest that most eye-gaze fixations are rather far away from the center of the viewport. Across contents and observers, gaze fixations are quasi-isotropically distributed in orientation. The average location of gaze fixation (across contents and observers) from the center of the view-port varies between 14 and 20 visual degrees and these values correspond to a shift in retina beyond the para and peri fovea, into the extra-perifoveal region. A saliency weighting model based on foveation, centered at the middle of the view-port seems to be a correct assumption in only 2.5% of the overall scenarios and is consequently questionable. Therefore there is a need to refine saliency modeling and weighting for quality assessment in case of panoramic viewing.

Published
2017
Full Text
View/download PDF

32. Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models

Author

Marie Guegan, Bertrand Jouve, Alberto Lumbreras, Julien Velcin, Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), Université Toulouse 1 Capitole - UT1 (FRANCE), Technicolor (FRANCE), Université Lumière-Lyon 2 (FRANCE), Laboratoire Entrepôts, Représentation & Ingénierie des Connaissances - ERIC (Lyon, France), Entrepôts, Représentation et Ingénierie des Connaissances (ERIC), Université Lumière - Lyon 2 (UL2)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon, Technicolor R & I [Cesson Sévigné], Technicolor, France, Amériques, Espagne – Sociétés, pouvoirs, acteurs (FRAMESPA), Université Toulouse - Jean Jaurès (UT2J)-Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques de Toulouse UMR5219 (IMT), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS), CIFRE, Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)

Subjects
Statistics and Probability, FOS: Computer and information sciences, Computer Science - Machine Learning, Non parametric clustering, Computer science, Probability density function, Machine Learning (stat.ML), 02 engineering and technology, 010501 environmental sciences, Machine learning, computer.software_genre, 01 natural sciences, Machine Learning (cs.LG), Traitement des images, Model-based clustering, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Statistics - Machine Learning, Component (UML), Multi-view clustering, 0202 electrical engineering, electronic engineering, information engineering, Feature (machine learning), Traitement du signal et de l'image, Synthèse d'image et réalité virtuelle, 0105 earth and related environmental sciences, Dirichlet Process (DP), business.industry, 020207 software engineering, ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.3: Clustering, Vision par ordinateur et reconnaissance de formes, DUAL (cognitive architecture), Intelligence artificielle, Mixture model, Dirichlet process, Chinese Restaurant Process (CRP), Computational Mathematics, Task (computing), ComputingMethodologies_PATTERNRECOGNITION, Artificial intelligence, Statistics, Probability and Uncertainty, business, computer
Abstract

International audience; We present a dual-view mixture model to cluster users based on their features and latent behavioral functions. Every component of the mixture model represents a probability density over a feature view for observed user attributes and a behavior view for latent behavioral functions that are indirectly observed through user actions or behaviors. Our task is to infer the groups of users as well as their latent behavioral functions. We also propose a non-parametric version based on a Dirichlet Process to automatically infer the number of clusters. We test the properties and performance of the model on a synthetic dataset that represents the participation of users in the threads of an online forum. Experiments show that dual-view models outperform single-view ones when one of the views lacks information.

Published
2017
Full Text
View/download PDF

33. Super-rays for Efficient Light Field Processing

Author

Neus Sabater, Matthieu Hog, Christine Guillemot, Technicolor R & I [Cesson Sévigné], Technicolor, Analysis representation, compression and communication of visual data (Sirocco), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes)

Subjects
business.industry, Computer science, Pipeline (computing), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, 02 engineering and technology, Aliasing, Component (UML), Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Key (cryptography), 020201 artificial intelligence & image processing, Computer vision, Segmentation, Artificial intelligence, Electrical and Electronic Engineering, business, Image resolution, Light field
Abstract

International audience; Light field acquisition devices allow capturing scenes with unmatched post-processing possibilities. However, the huge amount of high dimensional data poses challenging problems to light field processing in interactive time. In order to enable light field processing with a tractable complexity, in this paper, we address the problem of light field over-segmentation. We introduce the concept of super-ray, which is a grouping of rays within and across views, as a key component of a light field processing pipeline. The proposed approach is simple, fast, accurate, easily parallelisable, and does not need a dense depth estimation. We demonstrate experimentally the efficiency of the proposed approach on real and synthetic datasets, for sparsely and densely sampled light fields. As super-rays capture a coarse scene geometry information, we also present how they can be used for real time light field segmentation and correcting refocusing angular aliasing.

Published
2017
Full Text
View/download PDF

34. Role detection in online forums based on growth models for trees

Author

Marie Guegan, Bertrand Jouve, Julien Velcin, Alberto Lumbreras, Entrepôts, Représentation et Ingénierie des Connaissances (ERIC), Université Lumière - Lyon 2 (UL2)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon, Institut de Mathématiques de Toulouse UMR5219 (IMT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), and Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)

Subjects
Computer science, 02 engineering and technology, Machine learning, computer.software_genre, Clustering, [INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Simple (abstract algebra), 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, Growth models, discussion Forums, Cluster analysis, Social network, business.industry, Communication, [INFO.INFO-WB]Computer Science [cs]/Web, Growth model, Role detection, Computer Science Applications, Human-Computer Interaction, 020201 artificial intelligence & image processing, Data mining, Artificial intelligence, business, computer, Information Systems
Abstract

International audience; Some structural characteristics of online discussions have been successfully modeled in the recent years. When parameters of these models are properly estimated, the models are able to generate synthetic discussions that are structurally similar to the real discussions. A common aspect of these models is that they consider that all users behave according to the same model. In this paper, we combine a growth-model with an Expectation-Maximization algorithm that finds different parameters for different latent groups of users. We use this method to find the different roles that coexist in the community. Moreover, we analyze whether we can predict users behaviors based on their roles. Indeed, we show that predictions are improved for some of the roles when compared with a simple growth model.

Published
2017
Full Text
View/download PDF

35. Multiview approaches to event detection and scene analysis

Author

Fabio Antonacci, Slim Essid, Alexey Ozerov, Ngoc Q. K. Duong, Sanjeel Parekh, Romain Serizel, Augusto Sarti, Signal, Statistique et Apprentissage (S2A), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Département Images, Données, Signal (IDS), Télécom ParisTech, Technicolor R & I [Cesson Sévigné], Technicolor, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Dipartimento di Elettronica e Informazione, Politecnico di Milano [Milan] (POLIMI), Tuomas Virtanen, Mark D. Plumbley, and Dan Ellis

Subjects
Beamforming, Microphone array, Computer science, media_common.quotation_subject, Audio source separation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), Multichannel audio, Multimodal scene analysis, 02 engineering and technology, Representation learning, Presentation, Physics and Astronomy (all), Engineering (all), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Audio source localization and tracking, Data fusion, Joint audiovisual scene analysis, Matrix factorization, Multichannel Wiener filtering, Multiview scene analysis, Tensor factorization, Computer Science (all), 0202 electrical engineering, electronic engineering, information engineering, Selection (linguistics), Computer vision, Wiener filtering, media_common, business.industry, Event (computing), [SCCO.NEUR]Cognitive science/Neuroscience, 020206 networking & telecommunications, Sensor fusion, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], Multichannel, 020201 artificial intelligence & image processing, Artificial intelligence, business, Feature learning, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; This chapter addresses sound scene and event classification in multiview settings, that is, settings where the observations are obtained from multiple sensors, each sensor contributing a particular view of the data (e.g., audio microphones, video cameras, etc.). We briefly introduce some of the techniques that can be exploited to effectively combine the data conveyed by the different views under analysis for a better interpretation. We first provide a high-level presentation of generic methods that are particularly relevant in the context of multiview and multimodal sound scene analysis. Then, we more specifically present a selection of techniques used for audiovisual event detection and microphone array-based scene analysis.

Published
2017
Full Text
View/download PDF

36. Cotemporal Multi-View Video Segmentation

Author

Abdelaziz Djelouah, Edmond Boyer, Jean-Sébastien Franco, Patrick Pérez, George Drettakis, GRAPHics and DEsign with hEterogeneous COntent (GRAPHDECO), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Capture and Analysis of Shapes in Motion (MORPHEO ), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Technicolor [Cesson Sévigné], Technicolor, ANR-13-CORD-0003,SEMAPOLIS,Analyse sémantique visuelle et reconstruction 3D sémantisée d'environnements urbains(2013), and European Project: 611089,EC:FP7:ICT,FP7-ICT-2013-10,CR-PLAY(2013)

Subjects
Monocular, Computer science, Segmentation-based object categorization, business.industry, Multi-view images, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, 02 engineering and technology, Image segmentation, Viewpoints, Segmentation, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Motion correlation, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, Cosegmentation
Abstract

International audience; We address the problem of multi-view video segmentation of dynamic scenes in general and outdoor environments with possibly moving cameras. Multi-view methods for dynamic scenes usually rely on geometric calibration to impose spatial shape constraints between viewpoints. In this paper, we show that the calibration constraint can be relaxed while still getting competitive segmentation results using multi-view constraints. We introduce new multi-view cotemporality constraints through motion correlation cues, in addition to common appearance features used by co-segmentation methods to identify co-instances of objects. We also take advantage of learning based segmentation strategies by casting the problem as the selection of monocular proposals that satisfy multi-view constraints. This yields a fully automated method that can segment subjects of interest without any particular pre-processing stage. Results on several challenging outdoor datasets demonstrate the feasibility and robustness of our approach.

Published
2016
Full Text
View/download PDF

37. SPLeaP: Soft Pooling of Learned Parts for Image Classification

Author

Louis Chevallier, Frédéric Jurie, Joaquin Zepeda, Praveen Kulkarni, Patrick Pérez, Technicolor R & I [Cesson Sévigné], Technicolor, Equipe Image - Laboratoire GREYC - UMR6072, Groupe de Recherche en Informatique, Image et Instrumentation de Caen (GREYC), Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU)-Normandie Université (NU)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU), Technicolor [Cesson Sévigné], and Jurie, Frederic

Subjects
Contextual image classification, Association rule learning, business.industry, Computer science, Pooling, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, Machine learning, computer.software_genre, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Classifier (UML), computer, Parametric statistics
Abstract

International audience; The aggregation of image statistics – the so-called pooling step of image classification algorithms – as well as the construction of part-based models, are two distinct and well-studied topics in the literature. The former aims at leveraging a whole set of local descriptors that an image can contain (through spatial pyramids or Fisher vectors for instance) while the latter argues that only a few of the regions an image contains are actually useful for its classification. This paper bridges the two worlds by proposing a new pooling framework based on the discovery of useful parts involved in the pooling of local representations. The key contribution lies in a model integrating a boosted non-linear part clas-sifier as well as a parametric soft-max pooling component, both trained jointly with the image classifier. The experimental validation shows that the proposed model not only consistently surpasses standard pooling approaches but also improves over state-of-the-art part-based models, on several different and challenging classification tasks.

Published
2016

38. Hierarchical motion decomposition for dynamic scene parsing

Author

Patrick Bouthemy, Patrick Pérez, Juan-Manuel Perez-Rua, Tomas Crivelli, Space-timE RePresentation, Imaging and cellular dynamics of molecular COmplexes (SERPICO), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Technicolor [Cesson Sévigné], Technicolor, and IEEE

Subjects
Conditional random field, Video production, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, hierarchical motion decomposition, Scale-space segmentation, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, conditional random fields, Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, Segmentation, Computer vision, 0105 earth and related environmental sciences, Motion compensation, motion models, Segmentation-based object categorization, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Image segmentation, Index Terms— Video segmentation, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

Peer-reviewed paper accepted for presentation at the IEEE International Conference on Image Processing 2016; International audience; A number of applications in video analysis rely on a per-frame motion segmentation of the scene as key preprocess-ing step. Moreover, different settings in video production require extracting segmentation masks of multiple moving objects and object parts in a hierarchical fashion. In order to tackle this problem, we propose to analyze and exploit the compositional structure of scene motion to provide a segmen-tation which is not purely driven by local image information. Specifically, we leverage a hierarchical motion-based partition of the scene to capture a mid-level understanding of the dynamic video content. We present experimental results showing the strengths of this approach in comparison to current video segmentation approaches.

Published
2016
Full Text
View/download PDF

39. Learning clustering-based linear mappings for quantization noise removal

Author

Martin Alain, Christine Guillemot, Philippe Guillotel, Dominique Thoreau, Analysis representation, compression and communication of visual data (Sirocco ), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)

Subjects
HEVC, de-noising, Binary tree, business.industry, Noise reduction, De noising, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020206 networking & telecommunications, Pattern recognition, Data_CODINGANDINFORMATIONTHEORY, 02 engineering and technology, Linear map, linear mapping, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, regression, 020201 artificial intelligence & image processing, Artificial intelligence, Index Terms: clustering, business, Cluster analysis, Encoder, Decoding methods, Coding (social sciences), Mathematics
Abstract

International audience; This paper describes a novel scheme to reduce the quantization noise of compressed videos and improve the overall coding performances. The proposed scheme first consists in clustering noisy patches of the compressed sequence. Then, at the encoder side, linear mappings are learned for each cluster between the noisy patches and the corresponding source patches. The linear mappings are then transmitted to the decoder where they can be applied to perform de-noising. The method has been tested with the HEVC standard, leading to a bitrate saving of up to 9.63%.

Published
2016
Full Text
View/download PDF

40. Split and Match: Example-based Adaptive Patch Sampling for Unsupervised Style Transfer

Author

Julie Delon, Neus Sabater, Oriel Frigo, Pierre Hellier, Mathématiques Appliquées Paris 5 (MAP5 - UMR 8145), Université Paris Descartes - Paris 5 (UPD5)-Institut National des Sciences Mathématiques et de leurs Interactions (INSMI)-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, ANR-14-CE27-0019,MIRIAM,Restauration Multi-Images: des Mathématiques Appliqueés à l'Industrie de l'Imagerie.(2014), Frigo, Oriel, Appel à projets générique - Restauration Multi-Images: des Mathématiques Appliqueés à l'Industrie de l'Imagerie. - - MIRIAM2014 - ANR-14-CE27-0019 - Appel à projets générique - VALID, Mathématiques Appliquées à Paris 5 ( MAP5 - UMR 8145 ), Université Paris Descartes - Paris 5 ( UPD5 ) -Institut National des Sciences Mathématiques et de leurs Interactions-Centre National de la Recherche Scientifique ( CNRS ), and ANR-14-CE27-0019,MIRIAM,Restauration Multi-Images: des Mathématiques Appliqueés à l'Industrie de l'Imagerie. ( 2014 )

Subjects
Structure (mathematical logic), business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Pattern recognition, 02 engineering and technology, Iterative reconstruction, Partition (database), Image (mathematics), Visualization, Texture transfer, Image texture, Sampling (signal processing), [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

Peer-reviewed paper presented at IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016, Las Vegas, United States.; International audience; This paper presents a novel unsupervised method to transfer the style of an example image to a source image. The complex notion of image style is here considered as a local texture transfer, eventually coupled with a global color transfer. For the local texture transfer, we propose a new patch-based method based on an adaptive partition that captures the style of the example image and preserves the structure of the source image. More precisely, this example-based partition predicts how well a source patch matches an example patch. Results on various images show that out method outperforms the most recent techniques.

Published
2016

41. Determining occlusions from space and time image reconstructions

Author

Patrick Bouthemy, Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Pérez, Technicolor [Cesson Sévigné], Technicolor, Space-timE RePresentation, Imaging and cellular dynamics of molecular COmplexes (SERPICO), Inria Rennes – Bretagne Atlantique, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Spacetime, Exploit, Pixel, business.industry, Computation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 02 engineering and technology, 010501 environmental sciences, Occlusion detection, 01 natural sciences, Displacement field, 0202 electrical engineering, electronic engineering, information engineering, Leverage (statistics), 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, ComputingMethodologies_COMPUTERGRAPHICS, 0105 earth and related environmental sciences, Mathematics, Parametric statistics
Abstract

Peer-reviewed paper accepted for presentation at the IEEE Conference on Computer Vision and Pattern Recognition 2016, in Las Vegas, USA; International audience; The problem of localizing occlusions between consecutive frames of a video is important but rarely tackled on its own. In most works, it is tightly interleaved with the computation of accurate optical flows, which leads to a delicate chicken-and-egg problem. With this in mind, we propose a novel approach to occlusion detection where visibility or not of a point in next frame is formulated in terms of visual reconstruction. The key issue is now to determine how well a pixel in the first image can be " reconstructed " from co-located colors in the next image. We first exploit this reasoning at the pixel level with a new detection criterion. Contrary to the ubiquitous displaced-frame-difference and forward-backward flow vector matching, the proposed alternative does not critically depend on a pre-computed, dense displacement field, while being shown to be more effective. We then leverage this local modeling within an energy-minimization framework that delivers oc-clusion maps. An easy-to-obtain collection of parametric motion models is exploited within the energy to provide the required level of motion information. Our approach outper-forms state-of-the-art detection methods on the challenging MPI Sintel dataset.

Published
2016

42. Multichannel audio declipping

Author

Alexey Ozerov, Cagdas Bilen, Patrick Pérez, Technicolor R & I [Cesson Sévigné], Technicolor, ANR-14-CE27-0002,MAD,Inpainting de données audio manquantes(2014), Ozerov, Alexey, and Appel à projets générique - Inpainting de données audio manquantes - - MAD2014 - ANR-14-CE27-0002 - Appel à projets générique - VALID

Subjects
Channel (digital image), [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Speech recognition, audio declipping, Model parameters, generalized expectation-maximization, 02 engineering and technology, Data_CODINGANDINFORMATIONTHEORY, Set (abstract data type), 030507 speech-language pathology & audiology, 03 medical and health sciences, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, multichannel audio, Computer Science::Multimedia, 0202 electrical engineering, electronic engineering, information engineering, Nonnegative tensor factorization, Mathematics, full-rank spatial model, business.industry, nonnegative tensor factorization, 020206 networking & telecommunications, Pattern recognition, Covariance, Power (physics), Sound recording and reproduction, Computer Science::Sound, Spectrogram, Artificial intelligence, 0305 other medical science, business
Abstract

International audience; Audio declipping consists in recovering so-called clipped audio samples that are set to a maximum / minimum threshold. Many different approaches were proposed to solve this problem in case of single-channel (mono) recordings. However, while most of audio recordings are multichannel nowadays, there is no method designed specifically for multichannel audio declipping, where the inter-channel correlations may be efficiently exploited for a better declipping result. In this work we propose for the first time such a multichannel audio declipping method. Our method is based on representing a multichannel audio recording as a convolutive mixture of several audio sources, and on modeling the source power spectrograms and mixing filters by nonnegative tensor factorization model and full-rank covariance matrices, respectively. A generalized expectation-maximization algorithm is proposed to estimate model parameters. It is shown experimentally that the proposed multichannel audio de-clipping algorithm outperforms in average and in most cases a state-of-the-art single-channel declipping algorithm applied to each channel independently.

Published
2016

43. Sketching for Large-Scale Learning of Mixture Models

Author

Nicolas Keriven, Anthony Bourrier, Rémi Gribonval, Patrick Pérez, Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio (PANAMA), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), Technicolor [Cesson Sévigné], Technicolor, European Project: 277906,EC:FP7:ERC,ERC-2011-StG_20101014,PLEASE(2012), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), GIPSA - Vision and Brain Signal Processing (GIPSA-VIBS), Département Images et Signal (GIPSA-DIS), Grenoble Images Parole Signal Automatique (GIPSA-lab ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Grenoble Images Parole Signal Automatique (GIPSA-lab ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Université de Rennes (UR), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Keriven, Nicolas, and PLEASE: Projections, Learning, and Sparsity for Efficient data-processing - PLEASE - - EC:FP7:ERC2012-01-01 - 2016-12-31 - 277906 - VALID

Subjects
Statistics and Probability, FOS: Computer and information sciences, [MATH.MATH-PR] Mathematics [math]/Probability [math.PR], Scale (ratio), [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Iterative method, Computer science, compressive sensing, Context (language use), Machine Learning (stat.ML), 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, Synthetic data, Machine Learning (cs.LG), 010104 statistics & probability, Dimension (vector space), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Compressed Sensing, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, 0101 mathematics, 0105 earth and related environmental sciences, Numerical Analysis, compressed learning, database sketch, business.industry, Applied Mathematics, 020206 networking & telecommunications, Pattern recognition, gaussian mixture models, Mixture model, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Sketch, [MATH.MATH-PR]Mathematics [math]/Probability [math.PR], Computer Science - Learning, Compressed sensing, Kernel method, Computational Theory and Mathematics, compressive learning, Probability distribution, Artificial intelligence, Heuristics, business, Gaussian mixture, Algorithm, Analysis
Abstract

to appear in Information and Inference, a journal of the IMA (available online since December 2017); International audience; Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a " compressive learning " framework where we estimate model parameters from a sketch of the training data. This sketch is a collection of generalized moments of the underlying probability distribution of the data. It can be computed in a single pass on the training set, and is easily computable on streams or distributed datasets. The proposed framework shares similarities with compressive sensing, which aims at drastically reducing the dimension of high-dimensional signals while preserving the ability to reconstruct them. To perform the estimation task, we derive an iterative algorithm analogous to sparse reconstruction algorithms in the context of linear inverse problems. We exemplify our framework with the compressive estimation of a Gaussian Mixture Model (GMM), providing heuristics on the choice of the sketching procedure and theoretical guarantees of reconstruction. We experimentally show on synthetic data that the proposed algorithm yields results comparable to the classical Expectation-Maximization (EM) technique while requiring significantly less memory and fewer computations when the number of database elements is large. We further demonstrate the potential of the approach on real large-scale data (over 10 8 training samples) for the task of model-based speaker verification. Finally, we draw some connections between the proposed framework and approximate Hilbert space embedding of probability distributions using random features. We show that the proposed sketching operator can be seen as an innovative method to design translation-invariant kernels adapted to the analysis of GMMs. We also use this theoretical framework to derive information preservation guarantees, in the spirit of infinite-dimensional compressive sensing.

Published
2016
Full Text
View/download PDF

44. Aggregating Local Image Descriptors into Compact Codes

Author

Herve Jegou, Cordelia Schmid, Jorge Sanchez, Patrick Pérez, Florent Perronnin, Matthijs Douze, Multimedia content-based indexing (TEXMEX), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Xerox Research Centre Europe [Meylan], Xerox Company, Learning and recognition in vision (LEAR), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Service Expérimentation et Développement (SED [Grenoble]), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Technicolor R & I [Cesson Sévigné], Technicolor, QUAERO, ANR-07-BLAN-0328,GAIA,Géométrie Algorithmique Informationnelle et Applications(2007), European Project: 216529,EC:FP7:ICT,FP7-ICT-2007-1,PINVIEW(2008), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique, and SED [Grenoble]

Subjects
Fisher kernel, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, image retrieval, image search, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Image retrieval, Mathematics, Multi-core processor, business.industry, Applied Mathematics, Dimensionality reduction, Search engine indexing, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Byte, 020207 software engineering, Pattern recognition, Visualization, Computational Theory and Mathematics, Kernel (image processing), 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software, indexing
Abstract

International audience; This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image dataset takes about 250 ms on one processor core.

Published
2012
Full Text
View/download PDF

45. ROAM: a Rich Object Appearance Model with Application to Rotoscoping

Author

Ondrej Miksik, Patrick Pérez, Juan-Manuel Perez-Rua, Philip H. S. Torr, University of Oxford, Space-timE RePresentation, Imaging and cellular dynamics of molecular COmplexes (SERPICO), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Technicolor R & I [Cesson Sévigné], and Technicolor

Subjects
Structure (mathematical logic), FOS: Computer and information sciences, Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Initialization, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, 02 engineering and technology, Image segmentation, Object (computer science), Active appearance model, Computer graphics (images), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Computer vision, Artificial intelligence, business, Adaptation (computer science)
Abstract

International audience; Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer the artists a much better interactive control on the definition , editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given a first closed outline of this object. This model combines a collection of local foreground/background appearance models spread along the outline, a global appearance model of the enclosed object and a set of distinctive foreground landmarks. The structure of this rich appearance model allows simple initialization, efficient iterative optimization with exact minimization at each step, and on-line adaptation in videos. We demonstrate qualitatively and quantitatively the merit of this framework through comparisons with tools based on either dynamic seg-mentation with a closed curve or pixel-wise binary labelling.

Published
2016
Full Text
View/download PDF

46. Annealed learning based block transforms for HEVC video coding

Author

Saurabh Puri, Sebastien Lasserre, Patrick Le Callet, Institut de Recherche en Communications et en Cybernétique de Nantes (IRCCyN), Mines Nantes (Mines Nantes)-École Centrale de Nantes (ECN)-Ecole Polytechnique de l'Université de Nantes (EPUN), Université de Nantes (UN)-Université de Nantes (UN)-PRES Université Nantes Angers Le Mans (UNAM)-Centre National de la Recherche Scientifique (CNRS), Technicolor [Cesson Sévigné], and Technicolor

Subjects
Computer science, business.industry, Macroblock, 030229 sport sciences, 02 engineering and technology, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, Discrete cosine transform, Lapped transform, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, Algorithm, Encoder, Random access, ComputingMilieux_MISCELLANEOUS, Data compression, Coding (social sciences)
Abstract

Most of the recent video compression standards employ the Discrete Cosine Transform (DCT) for transforming the residual signal in order to remove spatial correlation and to achieve higher compression efficiency. However, by careful adaptation of transforms to the video content, a better set of integer transforms can be obtained. This paper proposes a new on-the-fly block-based transform optimization technique which involves first the classification of the residual blocks based on the cost of encoding the block, and then the generation of new optimized transforms for each class. An annealing based learning technique is further proposed in this paper in order to improve the performance of the optimization algorithm. The algorithm is tested using the latest HEVC test software where an optimized set of transforms is learned on the first frame of the HEVC test sequences and then applied to the subsequent frames in a Random Access (RA) and All Intra (AI) configuration. The results shows that this method can gain over 2% in terms of Bjontegaard Delta (BD)-rate compared to standard HEVC encoder in AI configuration and nearly 1.5% in RA.

Published
2016

47. Color Management in HDR Imaging

Author

Tania Pouli, Mekides Assefa Abebe, Mohamed-Chaker Larabi, Erik Reinhard, Technicolor [Cesson Sévigné], Technicolor, Synthèse et analyse d'images (XLIM-ASALI), XLIM (XLIM), Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS), and Université de Poitiers

Subjects
business.industry, Color correction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Color balance, 020207 software engineering, 02 engineering and technology, Tone mapping, Color management, 01 natural sciences, Luminance, law.invention, 010309 optics, Geography, High-dynamic-range imaging, law, Computer graphics (images), 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Chromatic scale, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, High dynamic range, ComputingMilieux_MISCELLANEOUS
Abstract

A large volume of research exists that addresses the mapping, compression, expansion, and other types of manipulation of the extended luminance range afforded by high dynamic range technologies. However, most of this research focuses exclusively on the luminance dimension, ignoring the chromatic information in images. This is particularly problematic given the parallel push toward extending not only the luminance range but also the chromatic range. In this chapter, we look at solutions that combine the ideas of high dynamic range imaging with color management approaches in different contexts.

Published
2016
Full Text
View/download PDF

48. Multi-reference combinatorial strategy towards longer long-term dense motion estimation

Author

Pierre-Henri Conze, Philippe Robert, Tomas Crivelli, Luce Morin, Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie (ICube), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Les Hôpitaux Universitaires de Strasbourg (HUS)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et Nanosciences Grand-Est (MNGE), Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS), Technicolor [Cesson Sévigné], Technicolor, Institut d'Électronique et des Technologies du numéRique (IETR), Université de Nantes (UN)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Réseau nanophotonique et optique, Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Matériaux et nanosciences d'Alsace (FMNGE), Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université de Nantes (UN)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), and Nantes Université (NU)-Université de Rennes 1 (UR1)

Subjects
Matching (graph theory), Computer science, Context (language use), 02 engineering and technology, Displacement (vector), Video editing, Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, Long-term motion estimation, Computer vision, Combinatorial integration, business.industry, Process (computing), Motion trajectories, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, optical-flow, Multi-reference frames, Term (time), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Algorithm, Software, Reference frame, Dense matching
Abstract

Long-term dense motion estimation based on multi-step optical flows is addressed.Optical flows are combined through multi-step integration and statistical selection.An analysis of available single-reference complexity reduction schemes is provided.Our new multi-reference frames processing reaches longer accurate displacement fields. This paper addresses the estimation of accurate long-term dense motion fields from videos of complex scenes. With computer vision applications such as video editing in mind, we exploit optical flows estimated with various inter-frame distances and combine them through multi-step integration and statistical selection (MISS). In this context, managing numerous combinations of multi-step optical flows requires a complexity reduction scheme to overcome computational and memory issues. Our contribution is two-fold. First, we provide an exhaustive analysis of available single-reference complexity reduction strategies. Second, we propose a simple and efficient alternative related to multi-reference frames multi-step integration and statistical selection (MR-MISS). Our method automatically inserts intermediate reference frames once matching failures are detected to re-generate the motion estimation process and re-correlates the resulting dense trajectories. By this way, it reaches longer accurate displacement fields while efficiently reducing the complexity. Experiments on challenging sequences reveal improved results compared to state-of-the-art methods including existing MISS schemes both in terms of complexity reduction and accuracy improvement.

Published
2016
Full Text
View/download PDF

49. Localization of Distributed EEG Sources in the Context of Epilepsy: A Simulation Study

Author

Isabelle Merlet, Laurent Albera, Rémi Gribonval, Fabrice Wendling, Pierre Comon, Hanna Becker, Technicolor [Cesson Sévigné], Technicolor, Laboratoire Traitement du Signal et de l'Image (LTSI), Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM), GIPSA - Communication Information and Complex Systems (GIPSA-CICS), Département Images et Signal (GIPSA-DIS), Grenoble Images Parole Signal Automatique (GIPSA-lab ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Grenoble Images Parole Signal Automatique (GIPSA-lab ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio (PANAMA), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), CNRS, ERC-StG-2011-277906, FP7, 2010 BLAN 0309 01, ANR, Conseil Régional PACA, Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de la Santé et de la Recherche Médicale (INSERM), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), and Becker, Hanna

Subjects
Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Biomedical Engineering, Biophysics, Context (language use), 02 engineering and technology, Electroencephalography, Machine learning, computer.software_genre, 03 medical and health sciences, Epilepsy, 0302 clinical medicine, Eeg data, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, medicine, Distributed source localization, Ictal, EEG, medicine.diagnostic_test, business.industry, 020206 networking & telecommunications, Pattern recognition, medicine.disease, Epileptic activity, distributed source localization, epilepsy, Artificial intelligence, Spatial extent, business, computer, 030217 neurology & neurosurgery, brain source imaging
Abstract

International audience; Objective: Surface EEG recordings are routinely performed for the diagnosis and management of epilepsy. More particularly, they can help to delineate the brain regions involved in interictal epileptic activity. This is achieved by applying distributed source localization algorithms to the EEG data. Over the last two decades, a multitude of different methods have been proposed. The objective of this paper consists in comparing the performance of eight representative algorithms taking into account recently developed methods. Methods: The performance comparison is based on realistic computer simulations in the context of epileptic source localization. Main findings: All tested algorithms generally permit to identify the source positions, but only some algorithms (STWV-DA, 4-ExSo-MUSIC, SVB-SCCD, cLORETA) also give an indication of the spatial extent of the sources. Localizing deep and mesial sources remains a challenging problem.

Published
2016
Full Text
View/download PDF

50. Audio declipping via nonnegative matrix factorization

Author

Patrick Pérez, Alexey Ozerov, Cagdas Bilen, Technicolor [Cesson Sévigné], Technicolor, ANR-14-CE27-0002,MAD,Inpainting de données audio manquantes(2014), Ozerov, Alexey, and Appel à projets générique - Inpainting de données audio manquantes - - MAD2014 - ANR-14-CE27-0002 - Appel à projets générique - VALID

Subjects
Audio inpainting, Signal processing, Audio signal, Noise measurement, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, business.industry, Speech recognition, nonneg-ative matrix factorization, audio declipping, Inpainting, generalized expectation-maximization, Pattern recognition, computer.software_genre, Itakura-Saito divergence, Matrix decomposition, Non-negative matrix factorization, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Source separation, Artificial intelligence, Audio signal processing, business, computer, Mathematics
Abstract

International audience; Audio inpainting and audio declipping are important problems in audio signal processing, which are encountered in various practical applications. A number of approaches has been proposed in the literature to address these problems, most successful of which are based on sparsity of the audio signals in certain dictionary representations. Non-negative matrix factorization (NMF) is another powerful tool that has been successfully used in applications such as audio source separation. In this paper we propose a new algorithm that makes use of a low rank NMF model to perform audio inpainting and declipping. In addition to utilizing for the first time the NMF model to perform audio inpainting in presence of arbitrary losses in time domain, the proposed approach also introduces a novel way to enforce additional constraints on the signal magnitude in order to improve the performance in declipping applications. The proposed approach is shown to have a comparable performance with the state of the art dictionary based methods while providing a number of advantages.

Published
2015
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results