Search

Despite the photorealistic novel view synthesis (NVS) performance achieved by the original 3D Gaussian splatting (3DGS), its rendering quality significantly degrades with sparse input views. This performance drop is mainly caused by the limited number of initial points generated from the sparse input, insufficient supervision during the training process, and inadequate regularization of the oversized Gaussian ellipsoids. To handle these issues, we propose the LoopSparseGS, a loop-based 3DGS framework for the sparse novel view synthesis task. In specific, we propose a loop-based Progressive Gaussian Initialization (PGI) strategy that could iteratively densify the initialized point cloud using the rendered pseudo images during the training process. Then, the sparse and reliable depth from the Structure from Motion, and the window-based dense monocular depth are leveraged to provide precise geometric supervision via the proposed Depth-alignment Regularization (DAR). Additionally, we introduce a novel Sparse-friendly Sampling (SFS) strategy to handle oversized Gaussian ellipsoids leading to large pixel errors. Comprehensive experiments on four datasets demonstrate that LoopSparseGS outperforms existing state-of-the-art methods for sparse-input novel view synthesis, across indoor, outdoor, and object-level scenes with various image resolutions., Comment: 13 pages, 10 figures

As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous deep-learning-based methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature., Comment: 13 pages, 12 figures, journal

The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA).While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation.

This paper explores how artificial intelligence (AI) technology can contribute to achieve progress on good health and well-being, one of the United Nations' 17 Sustainable Development Goals. It is estimated that one in ten of the global population lived with a mental disorder. Inspired by studies showing that engaging and viewing beautiful natural images can make people feel happier and less stressful, lead to higher emotional well-being, and can even have therapeutic values, we explore how AI can help to promote mental health by developing automatic algorithms for finding beautiful and happy images. We first construct a large image database consisting of nearly 20K very high resolution colour photographs of natural scenes where each image is labelled with beautifulness and happiness scores by about 10 observers. Statistics of the database shows that there is a good correlation between the beautifulness and happiness scores which provides anecdotal evidence to corroborate that engaging beautiful natural images can potentially benefit mental well-being. Building on this unique database, the very first of its kind, we have developed a deep learning based model for automatically predicting the beautifulness and happiness scores of natural images. Experimental results are presented to show that it is possible to develop AI algorithms to automatically assess an image's beautifulness and happiness values which can in turn be used to develop applications for promoting mental health and well-being.

Simultaneously achieving 3D reconstruction and new view synthesis for indoor environments has widespread applications but is technically very challenging. State-of-the-art methods based on implicit neural functions can achieve excellent 3D reconstruction results, but their performances on new view synthesis can be unsatisfactory. The exciting development of neural radiance field (NeRF) has revolutionized new view synthesis, however, NeRF-based models can fail to reconstruct clean geometric surfaces. We have developed a dual neural radiance field (Du-NeRF) to simultaneously achieve high-quality geometry reconstruction and view rendering. Du-NeRF contains two geometric fields, one derived from the SDF field to facilitate geometric reconstruction and the other derived from the density field to boost new view synthesis. One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field. This reduces shape-radiance ambiguity and enables geometry and color to benefit from each other during the learning process. Extensive experiments demonstrate that Du-NeRF can significantly improve the performance of novel view synthesis and 3D reconstruction for indoor environments and it is particularly effective in constructing areas containing fine geometries that do not obey multi-view color consistency., Comment: 20 pages, 8 figures

Despite much progress, achieving real-time high-fidelity head avatar animation is still difficult and existing methods have to trade-off between speed and quality. 3DMM based methods often fail to model non-facial structures such as eyeglasses and hairstyles, while neural implicit models suffer from deformation inflexibility and rendering inefficiency. Although 3D Gaussian has been demonstrated to possess promising capability for geometry representation and radiance field reconstruction, applying 3D Gaussian in head avatar creation remains a major challenge since it is difficult for 3D Gaussian to model the head shape variations caused by changing poses and expressions. In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering. The parametric morphable shape model is a Point-based Morphable Shape Model (PMSM) which uses points instead of meshes for 3D representation to achieve enhanced representation flexibility. The PMSM first converts the FLAME mesh to points by sampling on the surfaces as well as off the meshes to enable the reconstruction of not only surface-like structures but also complex geometries such as eyeglasses and hairstyles. By aligning these points with the head shape in an analysis-by-synthesis manner, the PMSM makes it possible to utilize 3D Gaussian for fine detail representation and appearance modeling, thus enabling the creation of high-fidelity avatars. We show that PSAvatar can reconstruct high-fidelity head avatars of a variety of subjects and the avatars can be animated in real-time ($\ge$ 25 fps at a resolution of 512 $\times$ 512 )., Comment: 13 pages, 10 figures

Given a new $6DoF$ camera pose in an indoor environment, we study the challenging problem of predicting the view from that pose based on a set of reference RGBD views. Existing explicit or implicit 3D geometry construction methods are computationally expensive while those based on learning have predominantly focused on isolated views of object categories with regular geometric structure. Differing from the traditional \textit{render-inpaint} approach to new view synthesis in the real indoor environment, we propose a conditional generative adversarial neural network (P2I-NET) to directly predict the new view from the given pose. P2I-NET learns the conditional distribution of the images of the environment for establishing the correspondence between the camera pose and its view of the environment, and achieves this through a number of innovative designs in its architecture and training lost function. Two auxiliary discriminator constraints are introduced for enforcing the consistency between the pose of the generated image and that of the corresponding real world image in both the latent feature space and the real world pose space. Additionally a deep convolutional neural network (CNN) is introduced to further reinforce this consistency in the pixel space. We have performed extensive new view synthesis experiments on real indoor datasets. Results show that P2I-NET has superior performance against a number of NeRF based strong baseline models. In particular, we show that P2I-NET is 40 to 100 times faster than these competitor techniques while synthesising similar quality images. Furthermore, we contribute a new publicly available indoor environment dataset containing 22 high resolution RGBD videos where each frame also has accurate camera pose parameters.

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively annotated data. This paper presents a novel BIQA method which overcomes this fundamental obstacle. Specifically, we design a pair of collaborative autoencoders (COAE) consisting of a content autoencoder (CAE) and a distortion autoencoder (DAE) that work together to extract content and distortion representations, which are shown to be highly descriptive of image quality. While the CAE follows a standard codec procedure, we introduce the CAE-encoded feature as an extra input to the DAE's decoder for reconstructing distorted images, thus effectively forcing DAE's encoder to extract distortion representations. The self-supervised learning framework allows the COAE including two feature extractors to be trained by almost unlimited amount of data, thus leaving limited samples with annotations to finetune a BIQA model. We will show that the proposed BIQA method achieves state-of-the-art performance and has superior generalization capability over other learning based models. The codes are available at: https://github.com/Macro-Zhou/NRIQA-VISOR/.

Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS's can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC are available at https://github.com/PengZai/ARIC., Comment: Aceepted by AAAI2023. Code and results available at https://github.com/PengZai/ARIC

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional CNNs lack the intelligence to capture long-term dependencies of different image regions. Following the success of applying Transformer models on natural language processing tasks, the medical image segmentation field has also witnessed growing interest in utilizing Transformers, due to their ability to capture long-range contextual information. However, unlike CNNs, Transformers lack the ability to learn local feature representations. Thus, to fully utilize the advantages of both CNNs and Transformers, we propose a hybrid encoder-decoder segmentation model (ConvTransSeg). It consists of a multi-layer CNN as the encoder for feature learning and the corresponding multi-level Transformer as the decoder for segmentation prediction. The encoder and decoder are interconnected in a multi-resolution manner. We compared our method with many other state-of-the-art hybrid CNN and Transformer segmentation models on binary and multiple class image segmentation tasks using several public medical image datasets, including skin lesion, polyp, cell and brain tissue. The experimental results show that our method achieves overall the best performance in terms of Dice coefficient and average symmetric surface distance measures with low model complexity and memory consumption. In contrast to most Transformer-based methods that we compared, our method does not require the use of pre-trained models to achieve similar or better performance. The code is freely available for research purposes on Github: (the link will be added upon acceptance)., Comment: 12 pages, 5 figures, 4 tables, also submitted to IEEE-TMI

Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the State-of-the-Art image clustering models, achieving accuracy performance gains ranging from $2.1\%$ to $15.9\%$. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote--sensing images., Comment: 39

User videos shared on social media platforms usually suffer from degradations caused by unknown proprietary processing procedures, which means that their visual quality is poorer than that of the originals. This paper presents a new general video restoration framework for the restoration of user videos shared on social media platforms. In contrast to most deep learning-based video restoration methods that perform end-to-end mapping, where feature extraction is mostly treated as a black box, in the sense that what role a feature plays is often unknown, our new method, termed Video restOration through adapTive dEgradation Sensing (VOTES), introduces the concept of a degradation feature map (DFM) to explicitly guide the video restoration process. Specifically, for each video frame, we first adaptively estimate its DFM to extract features representing the difficulty of restoring its different regions. We then feed the DFM to a convolutional neural network (CNN) to compute hierarchical degradation features to modulate an end-to-end video restoration backbone network, such that more attention is paid explicitly to potentially more difficult to restore areas, which in turn leads to enhanced restoration performance. We will explain the design rationale of the VOTES framework and present extensive experimental results to show that the new VOTES method outperforms various state-of-the-art techniques both quantitatively and qualitatively. In addition, we contribute a large scale real-world database of user videos shared on different social media platforms. Codes and datasets are available at https://github.com/luohongming/VOTES.git, Comment: This paper has been accepted by ACMMM2022

Single-image HDR reconstruction or inverse tone mapping (iTM) is a challenging task. In particular, recovering information in over-exposed regions is extremely difficult because details in such regions are almost completely lost. In this paper, we present a deep learning based iTM method that takes advantage of the feature extraction and mapping power of deep convolutional neural networks (CNNs) and uses a lightness prior to modulate the CNN to better exploit observations in the surrounding areas of the over-exposed regions to enhance the quality of HDR image reconstruction. Specifically, we introduce a Hierarchical Synthesis Network (HiSN) for inferring a HDR image from a LDR input and a Lightness Adpative Modulation Network (LAMN) to incorporate the the lightness prior knowledge in the inferring process. The HiSN hierarchically synthesizes the high-brightness component and the low-brightness component of the HDR image whilst the LAMN uses a lightness adaptive mask that separates detail-less saturated bright pixels from well-exposed lower light pixels to enable HiSN to better infer the missing information, particularly in the difficult over-exposed detail-less areas. We present experimental results to demonstrate the effectiveness of the new technique based on quantitative measures and visual comparisons. In addition, we present ablation studies of HiSN and visualization of the activation maps inside LAMN to help gain a deeper understanding of the internal working of the new iTM algorithm and explain why it can achieve much improved performance over state-of-the-art algorithms., Comment: 11 pages, 10 figures

In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obtain huge amounts of labeled data. Recently, self--supervised learning shows its outstanding capability to learn representations of images, especially the methods of instance discrimination. Comparing methods of instance discrimination, clustering--based methods not only view the transformations of the same image as ``positive" samples but also similar images. In this paper, we propose a new clustering-based method for representation learning. We first introduce a quantity to measure representations' discriminativeness and from which we show that even distribution requires the most discriminative representations. This provides a theoretical insight into why evenly distributing the images works well. We notice that only the even distributions that preserve representations' neighborhood relations are desirable. Therefore, we develop an algorithm that translates the outputs of a neural network to achieve the goal of evenly distributing the samples while preserving outputs' neighborhood relations. Extensive experiments have demonstrated that our method can learn representations that are as good as or better than the state of the art approaches, and that our method performs computationally efficiently and robustly on various RSI datasets., Comment: 14 pages

In real-world applications, such as sharing photos on social media platforms, images are always not only sub-sampled but also heavily compressed thus often containing various artefacts. Simple methods for enhancing the resolution of such images will exacerbate the artefacts, rendering them visually objectionable. In spite of its high practical values, super-resolving compressed images is not well studied in the literature. In this paper, we propose a novel compressed image super resolution (CISR) framework based on parallel and series integration of artefacts removal and resolution enhancement. Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM). The ARM and the REM work in parallel with both taking the compressed LR image as their inputs, at the same time they also work in series with the REM taking the output of the ARM as one of its inputs and the ARM taking the output of the REM as its other input. A technique called unfolding is introduced to recursively suppress the compression artefacts and restore the image resolution. A unique feature of our CISR system is that it exploits the parallel and series connections between the ARM and the REM, and recursive optimization to reduce the model's dependency on specific types of degradation thus making it possible to train a single model to super-resolve images compressed by different methods to different qualities. Codes and datasets are available at https://github.com/luohongming/CISR_PSI.git, Comment: This paper have been accepted by Elsevier Signal Processing

This paper presents a quarter Laplacian filter that can preserve corners and edges during image smoothing. Its support region is $2\times2$, which is smaller than the $3\times3$ support region of Laplacian filter. Thus, it is more local. Moreover, this filter can be implemented via the classical box filter, leading to high performance for real time applications. Finally, we show its edge preserving property in several image processing tasks, including image smoothing, texture enhancement, and low-light image enhancement. The proposed filter can be adopted in a wide range of image processing applications.

Weighted Gaussian Curvature is an important measurement for images. However, its conventional computation scheme has low performance, low accuracy and requires that the input image must be second order differentiable. To tackle these three issues, we propose a novel discrete computation scheme for the weighted Gaussian curvature. Our scheme does not require the second order differentiability. Moreover, our scheme is more accurate, has smaller support region and computationally more efficient than the conventional schemes. Therefore, our scheme holds promise for a large range of applications where the weighted Gaussian curvature is needed, for example, image smoothing, cartoon texture decomposition, optical flow estimation, etc.

There are large amount of valuable video archives in Video Home System (VHS) format. However, due to the analog nature, their quality is often poor. Compared to High-definition television (HDTV), VHS video not only has a dull color appearance but also has a lower resolution and often appears blurry. In this paper, we focus on the problem of translating VHS video to HDTV video and have developed a solution based on a novel unsupervised multi-task adversarial learning model. Inspired by the success of generative adversarial network (GAN) and CycleGAN, we employ cycle consistency loss, adversarial loss and perceptual loss together to learn a translation model. An important innovation of our work is the incorporation of super-resolution model and color transfer model that can solve unsupervised multi-task problem. To our knowledge, this is the first work that dedicated to the study of the relation between VHS and HDTV and the first computational solution to translate VHS to HDTV. We present experimental results to demonstrate the effectiveness of our solution qualitatively and quantitatively., Comment: MMM2020 final version

Estimating depth from RGB images can facilitate many computer vision tasks, such as indoor localization, height estimation, and simultaneous localization and mapping (SLAM). Recently, monocular depth estimation has obtained great progress owing to the rapid development of deep learning techniques. They surpass traditional machine learning-based methods by a large margin in terms of accuracy and speed. Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions. In this survey, we first introduce the datasets for depth estimation, and then give a comprehensive introduction of the methods from three perspectives: supervised learning-based methods, unsupervised learning-based methods, and sparse samples guidance-based methods. In addition, downstream applications that benefit from the progress have also been illustrated. Finally, we point out the future directions and conclude the paper.

Facial attributes in StyleGAN generated images are entangled in the latent space which makes it very difficult to independently control a specific attribute without affecting the others. Supervised attribute editing requires annotated training data which is difficult to obtain and limits the editable attributes to those with labels. Therefore, unsupervised attribute editing in an disentangled latent space is key to performing neat and versatile semantic face editing. In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing. By applying STIA-WO to GAN, we have developed a StyleGAN termed STGAN-WO which performs weight decomposition through utilizing the style vector to construct a fully controllable weight matrix to regulate image synthesis, and employs orthogonal regularization to ensure each entry of the style vector only controls one independent feature matrix. To further disentangle the facial attributes, STGAN-WO introduces a structure-texture independent architecture which utilizes two independently and identically distributed (i.i.d.) latent vectors to control the synthesis of the texture and structure components in a disentangled way. Unsupervised semantic editing is achieved by moving the latent code in the coarse layers along its orthogonal directions to change texture related attributes or changing the latent code in the fine layers to manipulate structure related ones. We present experimental results which show that our new STGAN-WO can achieve better attribute editing than state of the art methods., Comment: 11pages, 8 figures

Predicting depth from a single image is an attractive research topic since it provides one more dimension of information to enable machines to better perceive the world. Recently, deep learning has emerged as an effective approach to monocular depth estimation. As obtaining labeled data is costly, there is a recent trend to move from supervised learning to unsupervised learning to obtain monocular depth. However, most unsupervised learning methods capable of achieving high depth prediction accuracy will require a deep network architecture which will be too heavy and complex to run on embedded devices with limited storage and memory spaces. To address this issue, we propose a new powerful network with a recurrent module to achieve the capability of a deep network while at the same time maintaining an extremely lightweight size for real-time high performance unsupervised monocular depth prediction from video sequences. Besides, a novel efficient upsample block is proposed to fuse the features from the associated encoder layer and recover the spatial size of features with the small number of model parameters. We validate the effectiveness of our approach via extensive experiments on the KITTI dataset. Our new model can run at a speed of about 110 frames per second (fps) on a single GPU, 37 fps on a single CPU, and 2 fps on a Raspberry Pi 3. Moreover, it achieves higher depth accuracy with nearly 33 times fewer model parameters than state-of-the-art models. To the best of our knowledge, this work is the first extremely lightweight neural network trained on monocular video sequences for real-time unsupervised monocular depth estimation, which opens up the possibility of implementing deep learning-based real-time unsupervised monocular depth prediction on low-cost embedded devices.

Camera localization is a fundamental requirement in robotics and computer vision. This paper introduces a pose-to-image translation framework to tackle the camera localization problem. We present PoseGANs, a conditional generative adversarial networks (cGANs) based framework for the implementation of pose-to-image translation. PoseGANs feature a number of innovations including a distance metric based conditional discriminator to conduct camera localization and a pose estimation technique for generated camera images as a stronger constraint to improve camera localization performance. Compared with learning-based regression methods such as PoseNet, PoseGANs can achieve better performance with model sizes that are 70% smaller. In addition, PoseGANs introduce the view synthesis technique to establish the correspondence between the 2D images and the scene, \textit{i.e.}, given a pose, PoseGANs are able to synthesize its corresponding camera images. Furthermore, we demonstrate that PoseGANs differ in principle from structure-based localization and learning-based regressions for camera localization, and show that PoseGANs exploit the geometric structures to accomplish the camera localization task, and is therefore more stable than and superior to learning-based regressions which rely on local texture features instead. In addition to camera localization and view synthesis, we also demonstrate that PoseGANs can be successfully used for other interesting applications such as moving object elimination and frame interpolation in video sequences.

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data. However, adversarial training could overfit to a specific type of adversarial attack and also lead to standard accuracy drop on clean images. To this end, we propose a novel Class-Aware Domain Adaptation (CADA) method for adversarial defense without directly applying adversarial training. Specifically, we propose to learn domain-invariant features for adversarial examples and clean images via a domain discriminator. Furthermore, we introduce a class-aware component into the discriminator to increase the discriminative power of the network for adversarial examples. We evaluate our newly proposed approach using multiple benchmark datasets. The results demonstrate that our method can significantly improve the state-of-the-art of adversarial robustness for various attacks and maintain high performances on clean images.

The "curse of dimensionality" is a well-known problem in pattern recognition. A widely used approach to tackling the problem is a group of subspace methods, where the original features are projected onto a new space. The lower dimensional subspace is then used to approximate the original features for classification. However, most subspace methods were not originally developed for classification. We believe that direct adoption of these subspace methods for pattern classification should not be considered best practice. In this paper, we present a new information theory based algorithm for selecting subspaces, which can always result in superior performance over conventional methods. This paper makes the following main contributions: i) it improves a common practice widely used by practitioners in the field of pattern recognition, ii) it develops an information theory based technique for systematically selecting the subspaces that are discriminative and therefore are suitable for pattern recognition/classification purposes, iii) it presents extensive experimental results on a variety of computer vision and pattern recognition tasks to illustrate that the subspaces selected based on maximum mutual information criterion will always enhance performance regardless of the classification techniques used.

Classifiers embedded within human in the loop visual object recognition frameworks commonly utilise two sources of information: one derived directly from the imagery data of an object, and the other obtained interactively from user interactions. These computer vision frameworks exploit human high-level cognitive power to tackle particularly difficult visual object recognition tasks. In this paper, we present innovative techniques to combine the two sources of information intelligently for the purpose of improving recognition accuracy. We firstly employ standard algorithms to build two classifiers for the two sources independently, and subsequently fuse the outputs from these classifiers to make a conclusive decision. The two fusion techniques proposed are: i) a modified naive Bayes algorithm that adaptively selects an individual classifier's output or combines both to produce a definite answer, and ii) a neural network based algorithm which feeds the outputs of the two classifiers to a 4-layer feedforward network to generate a final output. We present extensive experimental results on 4 challenging visual recognition tasks to illustrate that the new intelligent techniques consistently outperform traditional approaches to fusing the two sources of information.

Supervised semantic segmentation normally assumes the test data being in a similar data domain as the training data. However, in practice, the domain mismatch between the training and unseen data could lead to a significant performance drop. Obtaining accurate pixel-wise label for images in different domains is tedious and labor intensive, especially for histopathology images. In this paper, we propose a dual adaptive pyramid network (DAPNet) for histopathological gland segmentation adapting from one stain domain to another. We tackle the domain adaptation problem on two levels: 1) the image-level considers the differences of image color and style; 2) the feature-level addresses the spatial inconsistency between two domains. The two components are implemented as domain classifiers with adversarial training. We evaluate our new approach using two gland segmentation datasets with H&E and DAB-H stains respectively. The extensive experiments and ablation study demonstrate the effectiveness of our approach on the domain adaptive segmentation task. We show that the proposed approach performs favorably against other state-of-the-art methods., Comment: MICCAI2019

Image denoising is the process of removing noise from noisy images, which is an image domain transferring task, i.e., from a single or several noise level domains to a photo-realistic domain. In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment. We tackle the domain alignment on two levels. 1) the feature-level prior is to learn domain-invariant features for corrupted images with different level noise; 2) the pixel-level prior is used to push the denoised images to the natural image manifold. The two image priors are based on $\mathcal{H}$-divergence theory and implemented by learning classifiers in adversarial training manners. We evaluate our approach on multiple datasets. The results demonstrate the effectiveness of our approach for robust image denoising on both synthetic and real-world noisy images. Furthermore, we show that the feature-level prior is capable of alleviating the discrepancy between different level noise. It can be used to improve the blind denoising performance in terms of distortion measures (PSNR and SSIM), while pixel-level prior can effectively improve the perceptual quality to ensure the realistic outputs, which is further validated by subjective evaluation.

We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features, we also implement a generative adversarial training mechanism to force the VAE to output realistic and natural images. We present experimental results to show that the VAE trained with our new method outperforms state of the art in generating face images with much clearer and more natural noses, eyes, teeth, hair textures as well as reasonable backgrounds. We also show that our method can learn powerful embeddings of input face images, which can be used to achieve facial attribute manipulation. Moreover we propose a multi-view feature extraction strategy to extract effective image representations, which can be used to achieve state of the art performance in facial attribute prediction., Comment: Accepted in Neurocomputing, 2019. arXiv admin note: text overlap with arXiv:1610.00291

Local windows are routinely used in computer vision and almost without exception the center of the window is aligned with the pixels being processed. We show that this conventional wisdom is not universally applicable. When a pixel is on an edge, placing the center of the window on the pixel is one of the fundamental reasons that cause many filtering algorithms to blur the edges. Based on this insight, we propose a new Side Window Filtering (SWF) technique which aligns the window's side or corner with the pixel being processed. The SWF technique is surprisingly simple yet theoretically rooted and very effective in practice. We show that many traditional linear and nonlinear filters can be easily implemented under the SWF framework. Extensive analysis and experiments show that implementing the SWF principle can significantly improve their edge preserving capabilities and achieve state of the art performances in applications such as image smoothing, denoising, enhancement, structure-preserving texture-removing, mutual-structure extraction, and HDR tone mapping. In addition to image filtering, we further show that the SWF principle can be extended to other applications involving the use of a local window. Using colorization by optimization as an example, we demonstrate that implementing the SWF principle can effectively prevent artifacts such as color leakage associated with the conventional implementation. Given the ubiquity of window based operations in computer vision, the new SWF technique is likely to benefit many more applications., Comment: 2019 CVPR

Video summarization has been extensively studied in the past decades. However, user-generated video summarization is much less explored since there lack large-scale video datasets within which human-generated video summaries are unambiguously defined and annotated. Toward this end, we propose a user-generated video summarization dataset - UGSum52 - that consists of 52 videos (207 minutes). In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries. To the best of our knowledge, it is currently the largest dataset for user-generated video summarization. Based on this dataset, we present FrameRank, an unsupervised video summarization method that employs a frame-to-frame level affinity graph to identify coherent and informative frames to summarize a video. We use the Kullback-Leibler(KL)-divergence-based graph to rank temporal segments according to the amount of semantic information contained in their frames. We illustrate the effectiveness of our method by applying it to three datasets SumMe, TVSum and UGSum52 and show it achieves state-of-the-art results., Comment: accepted by ICME 2019 oral

One issue with computer based histopathology image analysis is that the size of the raw image is usually very large. Taking the raw image as input to the deep learning model would be computationally expensive while resizing the raw image to low resolution would incur information loss. In this paper, we present a novel deep hybrid attention approach to breast cancer classification. It first adaptively selects a sequence of coarse regions from the raw image by a hard visual attention algorithm, and then for each such region it is able to investigate the abnormal parts based on a soft-attention mechanism. A recurrent network is then built to make decisions to classify the image region and also to predict the location of the image region to be investigated at the next time step. As the region selection process is non-differentiable, we optimize the whole network through a reinforcement approach to learn an optimal policy to classify the regions. Based on this novel Look, Investigate and Classify approach, we only need to process a fraction of the pixels in the raw image resulting in significant saving in computational resources without sacrificing performances. Our approach is evaluated on a public breast cancer histopathology database, where it demonstrates superior performance to the state-of-the-art deep learning approaches, achieving around 96\% classification accuracy while only 15% of raw pixels are used., Comment: Accepted to ISBI'19

With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data. In this letter, we present a novel content-based remote sensing image retrieval method based on Triplet deep metric learning convolutional neural network (CNN). By constructing a Triplet network with metric learning objective function, we extract the representative features of the images in a semantic space in which images from the same class are close to each other while those from different classes are far apart. In such a semantic space, simple metric measures such as Euclidean distance can be used directly to compare the similarity of images and effectively retrieve images of the same class. We also investigate a supervised and an unsupervised learning methods for reducing the dimensionality of the learned semantic features. We present comprehensive experimental results on two publicly available remote sensing image retrieval datasets and show that our method significantly outperforms state-of-the-art., Comment: 5 pages, 7 figures, 3 tables

Single image defogging is a classical and challenging problem in computer vision. Existing methods towards this problem mainly include handcrafted priors based methods that rely on the use of the atmospheric degradation model and learning based approaches that require paired fog-fogfree training example images. In practice, however, prior-based methods are prone to failure due to their own limitations and paired training data are extremely difficult to acquire. Inspired by the principle of CycleGAN network, we have developed an end-to-end learning system that uses unpaired fog and fogfree training images, adversarial discriminators and cycle consistency losses to automatically construct a fog removal system. Similar to CycleGAN, our system has two transformation paths; one maps fog images to a fogfree image domain and the other maps fogfree images to a fog image domain. Instead of one stage mapping, our system uses a two stage mapping strategy in each transformation path to enhance the effectiveness of fog removal. Furthermore, we make explicit use of prior knowledge in the networks by embedding the atmospheric degradation principle and a sky prior for mapping fogfree images to the fog images domain. In addition, we also contribute the first real world nature fog-fogfree image dataset for defogging research. Our multiple real fog images dataset (MRFID) contains images of 200 natural outdoor scenes. For each scene, there are one clear image and corresponding four foggy images of different fog densities manually selected from a sequence of images taken by a fixed camera over the course of one year. Qualitative and quantitative comparison against several state-of-the-art methods on both synthetic and real world images demonstrate that our approach is effective and performs favorably for recovering a clear image from a foggy image., Comment: Submitted to IEEE Transactions on Image Processing

6DOF camera relocalization is an important component of autonomous driving and navigation. Deep learning has recently emerged as a promising technique to tackle this problem. In this paper, we present a novel relative geometry-aware Siamese neural network to enhance the performance of deep learning-based methods through explicitly exploiting the relative geometry constraints between images. We perform multi-task learning and predict the absolute and relative poses simultaneously. We regularize the shared-weight twin networks in both the pose and feature domains to ensure that the estimated poses are globally as well as locally correct. We employ metric learning and design a novel adaptive metric distance loss to learn a feature that is capable of distinguishing poses of visually similar images from different locations. We evaluate the proposed method on public indoor and outdoor benchmarks and the experimental results demonstrate that our method can significantly improve localization performance. Furthermore, extensive ablation evaluations are conducted to demonstrate the effectiveness of different terms of the loss function.

In the computer research area, facial expression recognition is a hot research problem. Recent years, the research has moved from the lab environment to in-the-wild circumstances. It is challenging, especially under extreme poses. But current expression detection systems are trying to avoid the pose effects and gain the general applicable ability. In this work, we solve the problem in the opposite approach. We consider the head poses and detect the expressions within special head poses. Our work includes two parts: detect the head pose and group it into one pre-defined head pose class; do facial expression recognize within each pose class. Our experiments show that the recognition results with pose class grouping are much better than that of direct recognition without considering poses. We combine the hand-crafted features, SIFT, LBP and geometric feature, with deep learning feature as the representation of the expressions. The handcrafted features are added into the deep learning framework along with the high level deep learning features. As a comparison, we implement SVM and random forest to as the prediction models. To train and test our methodology, we labeled the face dataset with 6 basic expressions., Comment: Published on ICGIP2017

One of the challenges in the study of Generative Adversarial Networks (GANs) is the difficulty of its performance control. Lipschitz constraint is essential in guaranteeing training stability for GANs. Although heuristic methods such as weight clipping, gradient penalty and spectral normalization have been proposed to enforce Lipschitz constraint, it is still difficult to achieve a solution that is both practically effective and theoretically provably satisfying a Lipschitz constraint. In this paper, we introduce the boundedness and continuity ($BC$) conditions to enforce the Lipschitz constraint on the discriminator functions of GANs. We prove theoretically that GANs with discriminators meeting the BC conditions satisfy the Lipschitz constraint. We present a practically very effective implementation of a GAN based on a convolutional neural network (CNN) by forcing the CNN to satisfy the $BC$ conditions (BC-GAN). We show that as compared to recent techniques including gradient penalty and spectral normalization, BC-GANs not only have better performances but also lower computational complexity., Comment: 20 pages, 7 figures

Motion blur, out of focus, insufficient spatial resolution, lossy compression and many other factors can all cause an image to have poor quality. However, image quality is a largely ignored issue in traditional pattern recognition literature. In this paper, we use face detection and recognition as case studies to show that image quality is an essential factor which will affect the performances of traditional algorithms. We demonstrated that it is not the image quality itself that is the most important, but rather the quality of the images in the training set should have similar quality as those in the testing set. To handle real-world application scenarios where images with different kinds and severities of degradation can be presented to the system, we have developed a quality classified image analysis framework to deal with images of mixed qualities adaptively. We use deep neural networks first to classify images based on their quality classes and then design a separate face detector and recognizer for images in each quality class. We will present experimental results to show that our quality classified framework can accurately classify images based on the type and severity of image degradations and can significantly boost the performances of state-of-the-art face detector and recognizer in dealing with image datasets containing mixed quality images., Comment: 6 pages

One of the methods for stratifying different molecular classes of breast cancer is the Nottingham Prognostic Index Plus (NPI+) which uses breast cancer relevant biomarkers to stain tumour tissues prepared on tissue microarray (TMA). To determine the molecular class of the tumour, pathologists will have to manually mark the nuclei activity biomarkers through a microscope and use a semi-quantitative assessment method to assign a histochemical score (H-Score) to each TMA core. Manually marking positively stained nuclei is a time consuming, imprecise and subjective process which will lead to inter-observer and intra-observer discrepancies. In this paper, we present an end-to-end deep learning system which directly predicts the H-Score automatically. Our system imitates the pathologists' decision process and uses one fully convolutional network (FCN) to extract all nuclei region (tumour and non-tumour), a second FCN to extract tumour nuclei region, and a multi-column convolutional neural network which takes the outputs of the first two FCNs and the stain intensity description image as input and acts as the high-level decision making mechanism to directly output the H-Score of the input TMA image. To the best of our knowledge, this is the first end-to-end system that takes a TMA image as input and directly outputs a clinical score. We will present experimental results which demonstrate that the H-Scores predicted by our model have very high and statistically significant correlation with experienced pathologists' scores and that the H-Score discrepancy between our algorithm and the pathologists is on par with the inter-subject discrepancy between the pathologists.

Building on crucial insights into the determining factors of the visual integrity of an image and the property of deep convolutional neural network (CNN), we have developed the Deep Feature Consistent Deep Image Transformation (DFC-DIT) framework which unifies challenging one-to-many mapping image processing problems such as image downscaling, decolorization (colour to grayscale conversion) and high dynamic range (HDR) image tone mapping. We train one CNN as a non-linear mapper to transform an input image to an output image following what we term the deep feature consistency principle which is enforced through another pretrained and fixed deep CNN. This is the first work that uses deep learning to solve and unify these three common image processing tasks. We present experimental results to demonstrate the effectiveness of the DFC-DIT technique and its state of the art performances.

In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the first work that has successfully developed deep learning based solutions to these two traditional low-level image processing problems. This not only introduces new methods to tackle well-known image processing problems but also demonstrates the power of deep learning in solving traditional signal processing problems. Second, we have developed an effective deep learning algorithm based on insights into the properties of visual quality of images and the internal representation properties of a deep convolutional neural network (CNN). We train a deep CNN as a nonlinear transformation function to map a low bit depth image to higher bit depth or from a halftone image to a continuous tone image. We also employ another pretrained deep CNN as a feature extractor to derive visually important features to construct the objective function for the training of the mapping CNN. We present experimental results to demonstrate the effectiveness of the new deep learning based solutions., Comment: 12 pages

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent deep learning works such as style transfer, we employ a pre-trained deep convolutional neural network (CNN) and use its hidden features to define a feature perceptual loss for VAE training. Evaluated on the CelebA face dataset, we show that our model produces better results than other methods in the literature. We also show that our method can produce latent vectors that can capture the semantic information of face expressions and can be used to achieve state-of-the-art performance in facial attribute prediction., Comment: WACV

A popular approach to semantic image understanding is to manually tag images with keywords and then learn a mapping from vi- sual features to keywords. Manually tagging images is a subjective pro- cess and the same or very similar visual contents are often tagged with different keywords. Furthermore, not all tags have the same descriptive power for visual contents and large vocabulary available from natural language could result in a very diverse set of keywords. In this paper, we propose an unsupervised visual theme discovery framework as a better (more compact, efficient and effective) alternative to semantic represen- tation of visual contents. We first show that tag based annotation lacks consistency and compactness for describing visually similar contents. We then learn the visual similarity between tags based on the visual features of the images containing the tags. At the same time, we use a natural language processing technique (word embedding) to measure the seman- tic similarity between tags. Finally, we cluster tags into visual themes based on their visual similarity and semantic similarity measures using a spectral clustering algorithm. We conduct user studies to evaluate the effectiveness and rationality of the visual themes discovered by our unsu- pervised algorithm and obtains promising result. We then design three common computer vision tasks, example based image search, keyword based image search and image labelling to explore potential applica- tion of our visual themes discovery framework. In experiments, visual themes significantly outperforms tags on semantic image understand- ing and achieve state-of-art performance in all three tasks. This again demonstrate the effectiveness and versatility of proposed framework.

We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study. Motivated by the observation that certain convolutional channels of a Convolutional Neural Network (CNN) exhibit object specific responses, we seek to discover and exploit the convolutional channels of a CNN in which neurons are activated by the presence of specific objects in the input image. A method for explicitly fine-tuning a pre-trained CNN to induce an object specific channel (OSC) and systematically identifying it for the human face object has been developed. Based on the basic OSC features, we introduce a multi-resolution approach to constructing robust face heatmaps for fast face detection in unconstrained settings. We show that multi-resolution OSC can be used to develop state of the art face detectors which have the advantage of being simple and compact.

Bottom-up saliency, an early human visual processing, behaves like binary classification of interest and null hypothesis. Its discriminant power, mutual information of image features and class distribution, is closely related to saliency value by the well-known centre-surround theory. As classification accuracy very much depends on window sizes, the discriminant saliency (power) varies according to sampling scales. Discriminating power estimation in multi-scales framework needs integrating with wavelet transformation and then estimating statistical discrepancy of two consecutive scales (centre-surround windows) by Hidden Markov Tree (HMT) model. Finally, multi-scale discriminant saliency (MDIS) maps are combined by the maximum information rule to synthesize a final saliency map. All MDIS maps are evaluated with standard quantitative tools (NSS,LCC,AUC) on N.Bruce's database with ground truth data as eye-tracking locations ; as well assessed qualitatively by visual examination of individual cases. For evaluating MDIS against well-known AIM saliency method, simulations are needed and described in details with several interesting conclusions, drawn for further research directions.

This paper formulates bottom-up visual saliency as center surround conditional entropy and presents a fast and efficient technique for the computation of such a saliency map. It is shown that the new saliency formulation is consistent with self-information based saliency, decision-theoretic saliency and Bayesian definition of surprises but also faces the same significant computational challenge of estimating probability density in very high dimensional spaces with limited samples. We have developed a fast and efficient nonparametric method to make the practical implementation of these types of saliency maps possible. By aligning pixels from the center and surround regions and treating their location coordinates as random variables, we use a k-d partitioning method to efficiently estimating the center surround conditional entropy. We present experimental results on two publicly available eye tracking still image databases and show that the new technique is competitive with state of the art bottom-up saliency computational methods. We have also extended the technique to compute spatiotemporal visual saliency of video and evaluate the bottom-up spatiotemporal saliency against eye tracking data on a video taken onboard a moving vehicle with the driver's eye being tracked by a head mounted eye-tracker.

The bottom-up saliency, an early stage of humans' visual attention, can be considered as a binary classification problem between centre and surround classes. Discriminant power of features for the classification is measured as mutual information between distributions of image features and corresponding classes . As the estimated discrepancy very much depends on considered scale level, multi-scale structure and discriminant power are integrated by employing discrete wavelet features and Hidden Markov Tree (HMT). With wavelet coefficients and Hidden Markov Tree parameters, quad-tree like label structures are constructed and utilized in maximum a posterior probability (MAP) of hidden class variables at corresponding dyadic sub-squares. Then, a saliency value for each square block at each scale level is computed with discriminant power principle. Finally, across multiple scales is integrated the final saliency map by an information maximization rule. Both standard quantitative tools such as NSS, LCC, AUC and qualitative assessments are used for evaluating the proposed multi-scale discriminant saliency (MDIS) method against the well-know information based approach AIM on its released image collection with eye-tracking data. Simulation results are presented and analysed to verify the validity of MDIS as well as point out its limitation for further research direction., Comment: arXiv admin note: substantial text overlap with arXiv:1301.3964

The bottom-up saliency, an early stage of humans' visual attention, can be considered as a binary classification problem between center and surround classes. Discriminant power of features for the classification is measured as mutual information between features and two classes distribution. The estimated discrepancy of two feature classes very much depends on considered scale levels; then, multi-scale structure and discriminant power are integrated by employing discrete wavelet features and Hidden markov tree (HMT). With wavelet coefficients and Hidden Markov Tree parameters, quad-tree like label structures are constructed and utilized in maximum a posterior probability (MAP) of hidden class variables at corresponding dyadic sub-squares. Then, saliency value for each dyadic square at each scale level is computed with discriminant power principle and the MAP. Finally, across multiple scales is integrated the final saliency map by an information maximization rule. Both standard quantitative tools such as NSS, LCC, AUC and qualitative assessments are used for evaluating the proposed multiscale discriminant saliency method (MDIS) against the well-know information-based saliency method AIM on its Bruce Database wity eye-tracking data. Simulation results are presented and analyzed to verify the validity of MDIS as well as point out its disadvantages for further research direction., Comment: 16 pages, ICCSA 2013 - BIOCA session

Both pixel-based scale saliency (PSS) and basis project methods focus on multiscale analysis of data content and structure. Their theoretical relations and practical combination are previously discussed. However, no models have ever been proposed for calculating scale saliency on basis-projected descriptors since then. This paper extend those ideas into mathematical models and implement them in the wavelet-based scale saliency (WSS). While PSS uses pixel-value descriptors, WSS treats wavelet sub-bands as basis descriptors. The paper discusses different wavelet descriptors: discrete wavelet transform (DWT), wavelet packet transform (DWPT), quaternion wavelet transform (QWT) and best basis quaternion wavelet packet transform (QWPTBB). WSS saliency maps of different descriptors are generated and compared against other saliency methods by both quantitative and quanlitative methods. Quantitative results, ROC curves, AUC values and NSS values are collected from simulations on Bruce and Kootstra image databases with human eye-tracking data as ground-truth. Furthermore, qualitative visual results of saliency maps are analyzed and compared against each other as well as eye-tracking data inclusive in the databases., Comment: Partly published in ACIIDS 2013 - Kuala Lumpur Malaysia