Search

We have recently seen tremendous progress in diffusion advances for generating realistic human motions. Yet, they largely disregard the multi-human interactions. In this paper, we present InterGen, an effective diffusion-based approach that enables layman users to customize high-quality two-person interaction motions, with only text guidance. We first contribute a multimodal dataset, named InterHuman. It consists of about 107 M frames for diverse two-person interactions, with accurate skeletal motions and 23,337 natural language descriptions. For the algorithm side, we carefully tailor the motion diffusion model to our two-person interaction setting. To handle the symmetry of human identities during interactions, we propose two cooperative transformer-based denoisers that explicitly share weights, with a mutual attention mechanism to further connect the two denoising processes. Then, we propose a novel representation for motion input in our interaction diffusion model, which explicitly formulates the global relations between the two performers in the world frame. We further introduce two novel regularization terms to encode spatial relations, equipped with a corresponding damping scheme during the training of our interaction diffusion model. Extensive experiments validate the effectiveness of InterGen (https://tr3e.github.io/intergen-page/). Notably, it can generate more diverse and compelling two-person motions than previous methods and enables various downstream applications for human interactions. [ABSTRACT FROM AUTHOR]

Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably, whereas some traditional algorithm-based methods are more robust to feature noises, outlier nodes, and global transformation (e.g. rotation). In this paper, we propose a graph neural network (GNN) based approach to combine the advantage of data-driven and traditional methods. In the GNN framework, we transform traditional graph matching solvers as single-channel GNNs on the association graph and extend the single-channel architecture to the multi-channel network. The proposed model can be seen as an ensemble method that fuses multiple algorithms at every iteration. Instead of averaging the estimates at the end of the ensemble, in our approach, the independent iterations of the ensembled algorithms exchange their information after each iteration via a 1 × 1 channel-wise convolution layer. Experiments show that our model improves the performance of traditional algorithms significantly. In addition, we propose a random sampling strategy to reduce the computational complexity and GPU memory usage, so that the model is applicable to matching graphs with thousands of nodes. We evaluate the performance of our method on three tasks: geometric graph matching, semantic feature matching, and few-shot 3D shape classification. The proposed model performs comparably or outperforms the best existing GNN-based methods. [ABSTRACT FROM AUTHOR]

In this paper, we reveal and study a new challenging problem faced by object Re-IDentification (ReID), i.e., Coupled Noisy Labels (CNL) which refers to the Noisy Annotation (NA) and the accompanied Noisy Correspondence (NC). Specifically, NA refers to the wrongly-annotated identity of samples during manual labeling, and NC refers to the mismatched training pairs including false positives and false negatives whose correspondences are established based on the NA. Clearly, CNL will limit the success of the object ReID paradigm that simultaneously performs identity-aware discrimination learning on the data samples and pairwise similarity learning on the training pairs. To overcome this practical but ignored problem, we propose a robust object ReID method dubbed Learning with Coupled Noisy Labels (LCNL). In brief, LCNL first estimates the annotation confidences of samples and then adaptively divides the training pairs into four groups with the confidences to rectify the correspondences. After that, LCNL employs a novel objective function to achieve robust object ReID with theoretical guarantees. To verify the effectiveness of LCNL, we conduct extensive experiments on five benchmark datasets in single- and cross-modality object ReID tasks compared with 14 algorithms. The code could be accessed from https://github.com/XLearning-SCU/2024-IJCV-LCNL. [ABSTRACT FROM AUTHOR]

Dense vertex-to-vertex correspondence (i.e. registration) between 3D faces is a fundamental and challenging issue for 3D &2D face analysis. While the sparse landmarks are definite with anatomically ground-truth correspondence, the dense vertex correspondences on most facial regions are unknown. In this view, the current methods commonly result in reasonable but diverse solutions, which deviate from the optimum to the dense registration problem. In this paper, we revisit dense registration by a dimension-degraded problem, i.e. proportional segmentation of a line, and employ an iterative dividing and diffusing method to reach an optimum solution that is robust to different initializations. We formulate a local registration problem for dividing and a linear least-square problem for diffusing, with constraints on fixed features on a 3D facial surface. We further propose a multi-resolution algorithm to accelerate the computational process. The proposed method is linked to a novel local scaling metric, where we illustrate the physical significance as smooth adaptions for local cells of 3D facial shapes. Extensive experiments on public datasets demonstrate the effectiveness of the proposed method in various aspects. Generally, the proposed method leads to not only significantly better representations of 3D facial data, but also coherent local deformations with elegant grid architecture for fine-grained registrations. [ABSTRACT FROM AUTHOR]

Video Snapshot compressive imaging (SCI) is a promising technique to capture high-speed videos, which transforms the imaging speed from the detector to mask modulating and only needs a single measurement to capture multiple frames. The algorithm to reconstruct high-speed frames from the measurement plays a vital role in SCI. In this paper, we consider the promising reconstruction algorithm framework, namely plug-and-play (PnP), which is flexible to the encoding process comparing with other deep learning networks. One drawback of existing PnP algorithms is that they use a pre-trained denoising network as a plugged prior while the training data of the network might be different from the task in real applications. Towards this end, in this work, we propose the online PnP algorithm which can adaptively update the network's parameters within the PnP iteration; this makes the denoising network more applicable to the desired data in the SCI reconstruction. Furthermore, for color video imaging, RGB frames need to be recovered from Bayer pattern or named demosaicing in the camera pipeline. To address this challenge, we design a two-stage reconstruction framework to optimize these two coupled ill-posed problems and introduce a deep demosaicing prior specifically for video demosaicing in SCI. Extensive results on both simulation and real datasets verify the superiority of our adaptive deep PnP algorithm. Code is available at https://github.com/xyvirtualgroup/AdaptivePnP_SCI. [ABSTRACT FROM AUTHOR]

This paper studies a shuffled linear regression problem. As a variant of ordinary linear regression, it requires estimating not only the regression variable, but also permutational correspondences between the covariates and responses. While existing formulations require the underlying ground-truth correspondences to be an ideal bijection such that all pieces of data should match, such a requirement barely holds in real-world applications due to either missing data or outliers. In this work, we generalize the formulation of shuffled linear regression to a broader range of conditions where only a part of the data should correspond. To this end, the effective recovery condition and NP-hardness of the proposed formulation are also studied. Moreover, we present a simple yet effective algorithm for deriving the solution. Its global convergence property and convergence rate are also analyzed in detail. Distinct tasks validate the effectiveness of our proposed formulation and the solution method. [ABSTRACT FROM AUTHOR]

Winograd's minimal filtering algorithm has been widely used in 2-D Convolutional Neural Networks (CNNs) to reduce the number of multiplications for faster processing. However, it is only effective on convolutions with kernel size as 3 and stride as 1, because it suffers from significantly increased FLOPs and numerical accuracy problems for kernel size larger than 3 and fails on convolution with stride larger than 1. Worse, the extension to N–D convolution will intensify the numerical accuracy problem. These problems severely obstruct Winograd's minimal filtering algorithm's application to video analysis. In this paper, we propose a novel Decomposable Winograd Method (DWM) for the N–D convolution acceleration, which breaks through the limitation of original Winograd's minimal filtering algorithm to more general convolutions. DWM decomposes kernels with large size or stride>1 to several small kernels with stride as 1 for further applying Winograd algorithm, so that DWM can reduce the number of multiplications while keeping the numerical accuracy. It enables the fast exploration of larger kernel size, larger stride value, and higher dimensions in CNNs for high performance and accuracy and even the potential for new CNNs. Comparing against the original Winograd algorithm, the proposed DWM is able to support all kinds of N–D convolutions with a speedup of 1.44 × – 3.38 × , without affecting the numerical accuracy. [ABSTRACT FROM AUTHOR]

Surface comparison and matching is a challenging problem in computer vision. While elastic Riemannian metrics provide meaningful shape distances and point correspondences via the geodesic boundary value problem, solving this problem numerically tends to be difficult. Square root normal fields considerably simplify the computation of certain distances between parametrized surfaces. Yet they leave open the issue of finding optimal reparametrizations, which induce corresponding distances between unparametrized surfaces. This issue has concentrated much effort in recent years and led to the development of several numerical frameworks. In this paper, we take an alternative approach which bypasses the direct estimation of reparametrizations: we relax the geodesic boundary constraint using an auxiliary parametrization-blind varifold fidelity metric. This reformulation has several notable benefits. By avoiding altogether the need for reparametrizations, it provides the flexibility to deal with simplicial meshes of arbitrary topologies and sampling patterns. Moreover, the problem lends itself to a coarse-to-fine multi-resolution implementation, which makes the algorithm scalable to large meshes. Furthermore, this approach extends readily to higher-order feature maps such as square root curvature fields and is also able to include surface textures in the matching problem. We demonstrate these advantages on several examples, synthetic and real. [ABSTRACT FROM AUTHOR]

Given repeated observations of several subjects over time, i.e. a longitudinal data set, this paper introduces a new model to learn a classification of the shapes progression in an unsupervised setting: we automatically cluster a longitudinal data set in different classes without labels. Our method learns for each cluster an average shape trajectory (or representative curve) and its variance in space and time. Representative trajectories are built as the combination of pieces of curves. This mixture model is flexible enough to handle independent trajectories for each cluster as well as fork and merge scenarios. The estimation of such non linear mixture models in high dimension is known to be difficult because of the trapping states effect that hampers the optimisation of cluster assignments during training. We address this issue by using a tempered version of the stochastic EM algorithm. Finally, we apply our algorithm on different data sets. First, synthetic data are used to show that a tempered scheme achieves better convergence. We then apply our method to different real data sets: 1D RECIST score used to monitor tumors growth, 3D facial expressions and meshes of the hippocampus. In particular, we show how the method can be used to test different scenarios of hippocampus atrophy in ageing by using an heteregenous population of normal ageing individuals and mild cognitive impaired subjects. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GANs) successfully generate high quality data by learning a mapping from a latent vector to the data. Various studies assert that the latent space of a GAN is semantically meaningful and can be utilized for advanced data analysis and manipulation. To analyze the real data in the latent space of a GAN, it is necessary to build an inference mapping from the data to the latent vector. This paper proposes an effective algorithm to accurately infer the latent vector by utilizing GAN discriminator features. Our primary goal is to increase inference mapping accuracy with minimal training overhead. Furthermore, using the proposed algorithm, we suggest a conditional image generation algorithm, namely a spatially conditioned GAN. Extensive evaluations confirmed that the proposed inference algorithm achieved more semantically accurate inference mapping than existing methods and can be successfully applied to advanced conditional image generation tasks. [ABSTRACT FROM AUTHOR]

Active appearance models (AAMs) are one of the most popular and well-established techniques for modeling deformable objects in computer vision. In this paper, we study the problem of fitting AAMs using compositional gradient descent (CGD) algorithms. We present a unified and complete view of these algorithms and classify them with respect to three main characteristics: (i) cost function; (ii) type of composition; and (iii) optimization method. Furthermore, we extend the previous view by: (a) proposing a novel Bayesian cost function that can be interpreted as a general probabilistic formulation of the well-known project-out loss; (b) introducing two new types of composition, asymmetric and bidirectional, that combine the gradients of both image and appearance model to derive better convergent and more robust CGD algorithms; and (c) providing new valuable insights into existent CGD algorithms by reinterpreting them as direct applications of the Schur complement and the Wiberg method. Finally, in order to encourage open research and facilitate future comparisons with our work, we make the implementation of the algorithms studied in this paper publicly available as part of the Menpo Project (). [ABSTRACT FROM AUTHOR]

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support flexible bitwidth (1–8 bits) to further improve the computation efficiency, which raises a great challenge to find the optimal bitwidth for each layer: it requires domain experts to explore the vast design space trading off accuracy, latency, energy, and model size, which is both time-consuming and usually sub-optimal. There are plenty of specialized hardware accelerators for neural networks, but little research has been done to design specialized neural networks optimized for a particular hardware accelerator. The latter is demanding given the much longer design cycle of silicon than neural nets. Conventional quantization algorithm ignores the different hardware architectures and quantizes all the layers in a uniform way. In this paper, we introduce the Hardware-Aware Automated Quantization (HAQ) framework which automatically determine the quantization policy, and we take the hardware accelerator's feedback in the design loop. Rather than relying on proxy signals such as FLOPs and model size, we employ a hardware simulator to generate the direct feedback signals to the RL agent. Compared with other conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures. Our framework effectively reduced the latency by 1.4–1.95 × and the energy consumption by 1.9 × with negligible loss of accuracy compared with the fixed bitwidth (8 bits) quantization. Our framework reveals that the optimal policies on different hardware architectures (i.e., edge and cloud architectures) under different resource constraints (i.e., latency, energy and model size) are drastically different. We interpreted the implication of different quantization policies, which offer insights for both neural network architecture design and hardware architecture design. [ABSTRACT FROM AUTHOR]

Self-representation based subspace learning has shown its effectiveness in many applications. In this paper, we promote the traditional subspace representation learning by simultaneously taking advantages of multiple views and prior constraint. Accordingly, we establish a novel algorithm termed as Tensorized Multi-view Subspace Representation Learning. To exploit different views, the subspace representation matrices of different views are regarded as a low-rank tensor, which effectively models the high-order correlations of multi-view data. To incorporate prior information, a constraint matrix is devised to guide the subspace representation learning within a unified framework. The subspace representation tensor equipped with a low-rank constraint models elegantly the complementary information among different views, reduces redundancy of subspace representations, and then improves the accuracy of subsequent tasks. We formulate the model with a tensor nuclear norm minimization problem constrained with ℓ 2 , 1 -norm and linear equalities. The minimization problem is efficiently solved by using an Augmented Lagrangian Alternating Direction Minimization method. Extensive experimental results on diverse multi-view datasets demonstrate the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis, person re-identification, e-commerce, media editing, video surveillance, autonomous driving and virtual reality, etc. To perform well, models need to comprehensively perceive the semantic information and the differences between instances in a multi-human image, which is recently defined as the multi-human parsing task. In this paper, we first present a new large-scale database "Multi-human Parsing (MHP v2.0)" for algorithm development and evaluation to advance the research on understanding humans in crowded scenes. MHP v2.0 contains 25,403 elaborately annotated images with 58 fine-grained semantic category labels and 16 dense pose key point labels, involving 2–26 persons per image captured in real-world scenes from various viewpoints, poses, occlusion, interactions and background. We further propose a novel deep Nested Adversarial Network (NAN) model for multi-human parsing. NAN consists of three Generative Adversarial Network-like sub-nets, respectively performing semantic saliency prediction, instance-agnostic parsing and instance-aware clustering. These sub-nets form a nested structure and are carefully designed to learn jointly in an end-to-end way. NAN consistently outperforms existing state-of-the-art solutions on our MHP and several other datasets, including MHP v1.0, PASCAL-Person-Part and Buffy. NAN serves as a strong baseline to shed light on generic instance-level semantic part prediction and drive the future research on multi-human parsing. With the above innovations and contributions, we have organized the CVPR 2018 Workshop on Visual Understanding of Humans in Crowd Scene (VUHCS 2018) and the Fine-Grained Multi-human Parsing and Pose Estimation Challenge. These contributions together significantly benefit the community. Code and pre-trained models are available at https://github.com/ZhaoJ9014/Multi-Human-Parsing_MHP. [ABSTRACT FROM AUTHOR]

Spectral clustering is a hot topic and many spectral clustering algorithms have been proposed. These algorithms usually solve the discrete cluster indicator matrix by relaxing the original problems, obtaining the continuous solution and finally obtaining a discrete solution that is close to the continuous solution. However, such methods often result in a non-optimal solution to the original problem since the different steps solve different problems. In this paper, we propose a novel spectral clustering method, named as Enhanced Balanced Min Cut (EBMC). In the new method, a new normalized cut model is proposed, in which a set of balance parameters are learned to capture the differences among different clusters. An iterative method with proved convergence is used to effectively solve the new model without eigendecomposition. Theoretical analysis reveals the connection between EBMC and the classical normalized cut. Extensive experimental results show the effectiveness and efficiency of our approach in comparison with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of fast and efficient indexing techniques for sequences evolving in non-Euclidean spaces. This problem has several applications in the areas of human activity analysis, where there is a need to perform fast search, and recognition in very high dimensional spaces. The problem is made more challenging when representations such as landmarks, contours, and human skeletons etc. are naturally studied in a non-Euclidean setting where even simple operations are much more computationally intensive than their Euclidean counterparts. We propose a geometry and data adaptive symbolic framework that is shown to enable the deployment of fast and accurate algorithms for activity recognition, dynamic texture recognition, motif discovery. Toward this end, we present generalizations of key concepts of piece-wise aggregation and symbolic approximation for the case of non-Euclidean manifolds. We show that one can replace expensive geodesic computations with much faster symbolic computations with little loss of accuracy in activity recognition and discovery applications. The framework is general enough to work across both Euclidean and non-Euclidean spaces, depending on appropriate feature representations without compromising on the ultra-low bandwidth, high speed and high accuracy. The proposed methods are ideally suited for real-time systems and low complexity scenarios. [ABSTRACT FROM AUTHOR]

Deep neural network (DNN) architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of representation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities. In this paper, we attempt to unravel three aspects related to the robustness of DNNs for face recognition: (i) assessing the impact of deep architectures for face recognition in terms of vulnerabilities to attacks, (ii) detecting the singularities by characterizing abnormal filter response behavior in the hidden layers of deep networks; and (iii) making corrections to the processing pipeline to alleviate the problem. Our experimental evaluation using multiple open-source DNN-based face recognition networks, and three publicly available face databases demonstrates that the performance of deep learning based face recognition algorithms can suffer greatly in the presence of such distortions. We also evaluate the proposed approaches on four existing quasi-imperceptible distortions: DeepFool, Universal adversarial perturbations, l 2 , and Elastic-Net (EAD). The proposed method is able to detect both types of attacks with very high accuracy by suitably designing a classifier using the response of the hidden layers in the network. Finally, we present effective countermeasures to mitigate the impact of adversarial attacks and improve the overall robustness of DNN-based face recognition. [ABSTRACT FROM AUTHOR]

We address the problem of restoring a high-resolution face image from a blurry low-resolution input. This problem is difficult as super-resolution and deblurring need to be tackled simultaneously. Moreover, existing algorithms cannot handle face images well as low-resolution face images do not have much texture which is especially critical for deblurring. In this paper, we propose an effective algorithm by utilizing the domain-specific knowledge of human faces to recover high-quality faces. We first propose a facial component guided deep Convolutional Neural Network (CNN) to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image. However, the CNN based method cannot handle image details well. We further develop a novel exemplar-based detail enhancement algorithm via facial component matching. Extensive experiments show that the proposed method outperforms the state-of-the-art algorithms both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Subspace clustering methods partition the data that lie in or close to a union of subspaces in accordance with the subspace structure. Such methods with sparsity prior, such as sparse subspace clustering (SSC) (Elhamifar and Vidal in IEEE Trans Pattern Anal Mach Intell 35(11):2765-2781, 2013) with the sparsity induced by the ℓ1-norm, are demonstrated to be effective in subspace clustering. Most of those methods require certain assumptions, e.g. independence or disjointness, on the subspaces. However, these assumptions are not guaranteed to hold in practice and they limit the application of existing sparse subspace clustering methods. In this paper, we propose ℓ0-induced sparse subspace clustering (ℓ0-SSC). In contrast to the required assumptions, such as independence or disjointness, on subspaces for most existing sparse subspace clustering methods, we prove that ℓ0-SSC guarantees the subspace-sparse representation, a key element in subspace clustering, for arbitrary distinct underlying subspaces almost surely under the mild i.i.d. assumption on the data generation. We also present the “no free lunch” theorem which shows that obtaining the subspace representation under our general assumptions can not be much computationally cheaper than solving the corresponding ℓ0 sparse representation problem of ℓ0-SSC. A novel approximate algorithm named Approximate ℓ0-SSC (Aℓ0-SSC) is developed which employs proximal gradient descent to obtain a sub-optimal solution to the optimization problem of ℓ0-SSC with theoretical guarantee. The sub-optimal solution is used to build a sparse similarity matrix upon which spectral clustering is performed for the final clustering results. Extensive experimental results on various data sets demonstrate the superiority of Aℓ0-SSC compared to other competing clustering methods. Furthermore, we extend ℓ0-SSC to semi-supervised learning by performing label propagation on the sparse similarity matrix learnt by Aℓ0-SSC and demonstrate the effectiveness of the resultant semi-supervised learning method termed ℓ0-sparse subspace label propagation (ℓ0-SSLP). [ABSTRACT FROM AUTHOR]

Object tracking is challenging as target objects often undergo drastic appearance changes over time. Recently, adaptive correlation filters have been successfully applied to object tracking. However, tracking algorithms relying on highly adaptive correlation filters are prone to drift due to noisy updates. Moreover, as these algorithms do not maintain long-term memory of target appearance, they cannot recover from tracking failures caused by heavy occlusion or target disappearance in the camera view. In this paper, we propose to learn multiple adaptive correlation filters with both long-term and short-term memory of target appearance for robust object tracking. First, we learn a kernelized correlation filter with an aggressive learning rate for locating target objects precisely. We take into account the appropriate size of surrounding context and the feature representations. Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes. Third, we learn a complementary correlation filter with a conservative learning rate to maintain long-term memory of target appearance. We use the output responses of this long-term filter to determine if tracking failure occurs. In the case of tracking failures, we apply an incrementally learned detector to recover the target position in a sliding window fashion. Extensive experimental results on large-scale benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods in terms of efficiency, accuracy, and robustness. [ABSTRACT FROM AUTHOR]

Place recognition is a core competency for any visual simultaneous localization and mapping system. Identifying previously visited places enables the creation of globally accurate maps, robust relocalization, and multi-user mapping. To match one place to another, most state-of-the-art approaches must decide a priori what constitutes a place, often in terms of how many consecutive views should overlap, or how many consecutive images should be considered together. Unfortunately, such threshold dependencies limit their generality to different types of scenes. In this paper, we present a placeless place recognition algorithm using a novel match-density estimation technique that avoids heuristically discretizing the space. Instead, our approach considers place recognition as a problem of continuous matching between image streams, automatically discovering regions of high match density that represent overlapping trajectory segments. The algorithm uses well-studied statistical tests to identify the relevant matching regions which are subsequently passed to an absolute pose algorithm to recover the geometric alignment. We demonstrate the efficiency and accuracy of our methodology on three outdoor sequences, including a comprehensive evaluation against ground-truth from publicly available datasets that shows our approach outperforms several state-of-the-art algorithms for place recognition. Furthermore we compare our overall algorithm to the currently best performing system for global localization and show how we outperform the approach on challenging indoor and outdoor datasets. [ABSTRACT FROM AUTHOR]

Fitting algorithms for Active Appearance Models (AAMs) are usually considered to be robust but slow or fast but less able to generalize well to unseen variations. In this paper, we look into AAM fitting algorithms and make the following orthogonal contributions: We present a simple 'project-out' optimization framework that unifies and revises the most well-known optimization problems and solutions in AAMs. Based on this framework, we describe robust simultaneous AAM fitting algorithms the complexity of which is not prohibitive for current systems. We then go on one step further and propose a new approximate project-out AAM fitting algorithm which we coin Extended Project-Out Inverse Compositional (E-POIC). In contrast to current algorithms, E-POIC is both efficient and robust. Next, we describe a part-based AAM employing a translational motion model, which results in superior fitting and convergence properties. We also show that the proposed AAMs, when trained 'in-the-wild' using SIFT descriptors, perform surprisingly well even for the case of unseen unconstrained images. Via a number of experiments on unconstrained human and animal face databases, we show that our combined contributions largely bridge the gap between exact and current approximate methods for AAM fitting and perform comparably with state-of-the-art face alignment systems. [ABSTRACT FROM AUTHOR]

This paper presents a generalized version of the classic projective reconstruction theorem which helps to choose or assess depth constraints for projective depth estimation algorithms. The theorem shows that projective reconstruction is possible under a much weaker constraint than requiring all estimated projective depths to be nonzero. This result enables us to present classes of depth constraints under which any reconstruction of cameras and points projecting into given image points is projectively equivalent to the true camera-point configuration. It also completely specifies the possible wrong configurations allowed by other constraints. We demonstrate the application of the theorem by analysing several constraints used in the literature, as well as presenting new constraints with desirable properties. We mention some of the implications of our results on iterative depth estimation algorithms and projective reconstruction via rank minimization. Our theory is verified by running experiments on both synthetic and real data. [ABSTRACT FROM AUTHOR]

Image cropping is a common operation used to improve the visual quality of photographs. In this paper, we present an automatic cropping technique that accounts for the two primary considerations of people when they crop: removal of distracting content, and enhancement of overall composition. Our approach utilizes a large training set consisting of photos before and after cropping by expert photographers to learn how to evaluate these two factors in a crop. In contrast to the many methods that exist for general assessment of image quality, ours specifically examines differences between the original and cropped photo in solving for the crop parameters. To this end, several novel image features are proposed to model the changes in image content and composition when a crop is applied. The effectiveness of each feature is empirically analyzed in determining a final feature set for crop computation. Our experiments demonstrate improvements of our method over recent cropping algorithms on a broad range of images. [ABSTRACT FROM AUTHOR]

In this paper, we address the problems of contour detection, bottom-up grouping, object detection and semantic segmentation on RGB-D data. We focus on the challenging setting of cluttered indoor scenes, and evaluate our approach on the recently introduced NYU-Depth V2 (NYUD2) dataset (Silberman et al., ECCV, ). We propose algorithms for object boundary detection and hierarchical segmentation that generalize the $$gPb-ucm$$ approach of Arbelaez et al. (TPAMI, ) by making effective use of depth information. We show that our system can label each contour with its type (depth, normal or albedo). We also propose a generic method for long-range amodal completion of surfaces and show its effectiveness in grouping. We train RGB-D object detectors by analyzing and computing histogram of oriented gradients on the depth image and using them with deformable part models (Felzenszwalb et al., TPAMI, ). We observe that this simple strategy for training object detectors significantly outperforms more complicated models in the literature. We then turn to the problem of semantic segmentation for which we propose an approach that classifies superpixels into the dominant object categories in the NYUD2 dataset. We design generic and class-specific features to encode the appearance and geometry of objects. We also show that additional features computed from RGB-D object detectors and scene classifiers further improves semantic segmentation accuracy. In all of these tasks, we report significant improvements over the state-of-the-art. [ABSTRACT FROM AUTHOR]

This paper presents a new perspective for 3D scene understanding by reasoning object stability and safety using intuitive mechanics. Our approach utilizes a simple observation that, by human design, objects in static scenes should be stable in the gravity field and be safe with respect to various physical disturbances such as human activities. This assumption is applicable to all scene categories and poses useful constraints for the plausible interpretations (parses) in scene understanding. Given a 3D point cloud captured for a static scene by depth cameras, our method consists of three steps: (i) recovering solid 3D volumetric primitives from voxels; (ii) reasoning stability by grouping the unstable primitives to physically stable objects by optimizing the stability and the scene prior; and (iii) reasoning safety by evaluating the physical risks for objects under physical disturbances, such as human activity, wind or earthquakes. We adopt a novel intuitive physics model and represent the energy landscape of each primitive and object in the scene by a disconnectivity graph (DG). We construct a contact graph with nodes being 3D volumetric primitives and edges representing the supporting relations. Then we adopt a Swendson-Wang Cuts algorithm to partition the contact graph into groups, each of which is a stable object. In order to detect unsafe objects in a static scene, our method further infers hidden and situated causes (disturbances) in the scene, and then introduces intuitive physical mechanics to predict possible effects (e.g., falls) as consequences of the disturbances. In experiments, we demonstrate that the algorithm achieves a substantially better performance for (i) object segmentation, (ii) 3D volumetric recovery, and (iii) scene understanding with respect to other state-of-the-art methods. We also compare the safety prediction from the intuitive mechanics model with human judgement. [ABSTRACT FROM AUTHOR]

Object tracking is the process of determining the states of a target in consecutive video frames based on properties of motion and appearance consistency. In this paper, we propose a consistent low-rank sparse tracker (CLRST) that builds upon the particle filter framework for tracking. By exploiting temporal consistency, the proposed CLRST algorithm adaptively prunes and selects candidate particles. By using linear sparse combinations of dictionary templates, the proposed method learns the sparse representations of image regions corresponding to candidate particles jointly by exploiting the underlying low-rank constraints. In addition, the proposed CLRST algorithm is computationally attractive since temporal consistency property helps prune particles and the low-rank minimization problem for learning joint sparse representations can be efficiently solved by a sequence of closed form update operations. We evaluate the proposed CLRST algorithm against $$14$$ state-of-the-art tracking methods on a set of $$25$$ challenging image sequences. Experimental results show that the CLRST algorithm performs favorably against state-of-the-art tracking methods in terms of accuracy and execution time. [ABSTRACT FROM AUTHOR]

Automatic understanding of human affect using visual signals is of great importance in everyday human–machine interactions. Appraising human emotional states, behaviors and reactions displayed in real-world settings, can be accomplished using latent continuous dimensions (e.g., the circumplex model of affect). Valence (i.e., how positive or negative is an emotion) and arousal (i.e., power of the activation of the emotion) constitute popular and effective representations for affect. Nevertheless, the majority of collected datasets this far, although containing naturalistic emotional states, have been captured in highly controlled recording conditions. In this paper, we introduce the Aff-Wild benchmark for training and evaluating affect recognition algorithms. We also report on the results of the First Affect-in-the-wild Challenge (Aff-Wild Challenge) that was recently organized in conjunction with CVPR 2017 on the Aff-Wild database, and was the first ever challenge on the estimation of valence and arousal in-the-wild. Furthermore, we design and extensively train an end-to-end deep neural architecture which performs prediction of continuous emotion dimensions based on visual cues. The proposed deep learning architecture, AffWildNet, includes convolutional and recurrent neural network layers, exploiting the invariant properties of convolutional features, while also modeling temporal dynamics that arise in human behavior via the recurrent layers. The AffWildNet produced state-of-the-art results on the Aff-Wild Challenge. We then exploit the AffWild database for learning features, which can be used as priors for achieving best performances both for dimensional, as well as categorical emotion recognition, using the RECOLA, AFEW-VA and EmotiW 2017 datasets, compared to all other methods designed for the same goal. The database and emotion recognition models are available at http://ibug.doc.ic.ac.uk/resources/first-affect-wild-challenge. [ABSTRACT FROM AUTHOR]

An approach is proposed for recovering affine correspondences (ACs) from orientation- and scale-covariant, e.g., SIFT, features exploiting pre-estimated epipolar geometry. The method calculates the affine parameters consistent with the epipolar geometry from the point coordinates and the scales and rotations which the feature detector obtains. The proposed closed-form solver returns a single solution and is extremely fast, i.e., 0.5 μ seconds on average. Possible applications include estimating the homography from a single upgraded correspondence and, also, estimating the surface normal for each correspondence found in a pre-calibrated image pair (e.g., stereo rig). As the second contribution, we propose a minimal solver that estimates the relative pose of a vehicle-mounted camera from a single SIFT correspondence with the corresponding surface normal obtained from, e.g., upgraded ACs. The proposed algorithms are tested both on synthetic data and on a number of publicly available real-world datasets. Using the upgraded features and the proposed solvers leads to a significant speed-up in the homography, multi-homography and relative pose estimation problems with better or comparable accuracy to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The past decade has witnessed the rapid development of autonomous driving systems. However, it remains a daunting task to achieve full autonomy, especially when it comes to understanding the ever-changing, complex driving scenes. To alleviate the difficulty of perception, self-driving vehicles are usually equipped with a suite of sensors (e.g., cameras, LiDARs), hoping to capture the scenes with overlapping perspectives to minimize blind spots. Fusing these data streams and exploiting their complementary properties is thus rapidly becoming the current trend. Nonetheless, combining data that are captured by different sensors with drastically different ranging/ima-ging mechanisms is not a trivial task; instead, many factors need to be considered and optimized. If not careful, data from one sensor may act as noises to data from another sensor, with even poorer results by fusing them. Thus far, there has been no in-depth guidelines to designing the multi-modal fusion based 3D perception algorithms. To fill in the void and motivate further investigation, this survey conducts a thorough study of tens of recent deep learning based multi-modal 3D detection networks (with a special emphasis on LiDAR-camera fusion), focusing on their fusion stage (i.e., when to fuse), fusion inputs (i.e., what to fuse), and fusion granularity (i.e., how to fuse). These important design choices play a critical role in determining the performance of the fusion algorithm. In this survey, we first introduce the background of popular sensors used for self-driving, their data properties, and the corresponding object detection algorithms. Next, we discuss existing datasets that can be used for evaluating multi-modal 3D object detection algorithms. Then we present a review of multi-modal fusion based 3D detection networks, taking a close look at their fusion stage, fusion input and fusion granularity, and how these design choices evolve with time and technology. After the review, we discuss open challenges as well as possible solutions. We hope that this survey can help researchers to get familiar with the field and embark on investigations in the area of multi-modal 3D object detection. [ABSTRACT FROM AUTHOR]

We propose a novel minimal solver for sphere fitting via its 2D central projection, i.e., a special ellipse. The input of the presented algorithm consists of contour points detected in a camera image. General ellipse fitting problems require five contour points. However, taking advantage of the isotropic spherical target, three points are enough to define the tangent cone parameters of the sphere. This yields the sought ellipse parameters. Similarly, the sphere center can be estimated from the cone if the radius is known. These proposed geometric methods are rapid, numerically stable, and easy to implement. Experimental results—on synthetic, photorealistic, and real images—showcase the superiority of the proposed solutions to the state-of-the-art methods. A real-world LiDAR-camera calibration application justifies the utility of the sphere-based approach resulting in an error below a few centimeters. [ABSTRACT FROM AUTHOR]

We give robust recovery results for synchronization on the rotation group, SO (D) . In particular, we consider an adversarial corruption setting, where a limited percentage of the observations are arbitrarily corrupted. We develop a novel algorithm that exploits Tukey depth in the tangent space of SO (D) . This algorithm, called Depth Descent Synchronization, exactly recovers the underlying rotations up to an outlier percentage of 1 / (D (D - 1) + 2) , which corresponds to 1/4 for SO (2) and 1/8 for SO (3) . In the case of SO (2) , we demonstrate that a variant of this algorithm converges linearly to the ground truth rotations. We implement this algorithm for the case of SO (3) and demonstrate that it performs competitively on baseline synthetic data. [ABSTRACT FROM AUTHOR]

Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite limited. Addressing such problem, we present a novel domain-adaptive approach called AdaStereo that aims to align multi-level representations for deep stereo matching networks. Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline. Firstly, we propose a non-adversarial progressive color transfer algorithm for input image-level alignment. Secondly, we design an efficient parameter-free cost normalization layer for internal feature-level alignment. Lastly, a highly related auxiliary task, self-supervised occlusion-aware reconstruction is presented to narrow the gaps in output space. We perform intensive ablation studies and break-down comparisons to validate the effectiveness of each proposed module. With no extra inference overhead and only a slight increase in training complexity, our AdaStereo models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo, even outperforming some state-of-the-art disparity networks finetuned with target-domain ground-truths. Moreover, based on two additional evaluation metrics, the superiority of our domain-adaptive stereo matching pipeline is further uncovered from more perspectives. Finally, we demonstrate that our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments. [ABSTRACT FROM AUTHOR]

Point cloud is an essential format for three-dimensional (3-D) object modelling and interaction in Augmented Reality and Virtual Reality applications. In the current state of the art video-based point cloud compression (V-PCC), a dynamic point cloud is projected onto geometry and attribute videos patch by patch, each represented by its texture, depth, and occupancy map for reconstruction. To deal with occlusion, each patch is projected onto near and far depth fields in the geometry video. Once there are artifacts on the compressed two-dimensional (2-D) geometry video, they would be propagated to the 3-D point-cloud frames. In addition, in the lossy compression, there always exists a tradeoff between the rate of bitstream and distortion. Although some geometry-related methods were proposed to attenuate these artifacts and improve the coding efficiency, the interactive correlation between projected near and far depth fields has been ignored. Moreover, the non-linear representation ability of Convolutional Neural Network has not been fully considered. Therefore, we propose a learning-based approach to remove the geometry artifacts and improve the compressing efficiency. We have the following contributions. We devise a two-step method working on the near and far depth fields decomposed from geometry. The first stage is learning-based Pseudo-Motion Compensation. The second stage exploits the potential of the strong correlations between near and far depth fields. Our proposed algorithm is embedded in the V-PCC reference software. To the best of our knowledge, this is the first learning-based solution of the geometry artifacts removal in V-PCC. The extensive experimental results show that the proposed approach achieves significant gains on geometry artifacts removal and quality improvement of 3-D point-cloud reconstruction compared to the state-of-the-art schemes. [ABSTRACT FROM AUTHOR]

Caricature is an artistic drawing created to abstract or exaggerate facial features of a person. Rendering visually pleasing caricatures is a difficult task that requires professional skills, and thus it is of great interest to design a method to automatically generate such drawings. To deal with large shape changes, we propose an algorithm based on a semantic shape transform to produce diverse and plausible shape exaggerations. Specifically, we predict pixel-wise semantic correspondences and perform image warping on the input photo to achieve dense shape transformation. We show that the proposed framework is able to render visually pleasing shape exaggerations while maintaining their facial structures. In addition, our model allows users to manipulate the shape via the semantic map. We demonstrate the effectiveness of our approach on a large photograph-caricature benchmark dataset with comparisons to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the field of salient object detection where the purpose is to accurately detect and segment the most salient object in a scene. Several measures (e.g., area-under-the-curve, F1-measure, average precision, etc.) have been used to evaluate the similarity between a foreground map and a ground-truth map. The existing measures are based on pixel-wise errors and often ignore the structural similarities. Behavioral vision studies, however, have shown that the human visual system is highly sensitive to structures in scenes. Here, we propose a novel, efficient (0.005 s per image), and easy to calculate measure known as S-measure (structural measure) to evaluate foreground maps. Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a foreground map and a ground-truth map. We demonstrate superiority of our measure over existing ones using 4 meta-measures on 5 widely-used benchmark datasets. Furthermore, we conduct a behavioral judgment study over a new database. Data from 45 subjects shows that on average they preferred the saliency maps chosen by our measure over the saliency maps chosen by the state-of-the-art measures. Our experimental results offer new insights into foreground map evaluation where current measures fail to truly examine the strengths and weaknesses of models. Code: https://github.com/DengPingFan/S-measure. [ABSTRACT FROM AUTHOR]

Objects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects travel a considerable distance during exposure time of a single frame, and therefore, their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by general trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. By postprocessing, non-causal Tracking by Deblatting estimates continuous, complete, and accurate object trajectories for the whole sequence. Tracked objects are precisely localized with higher temporal resolution than by conventional trackers. Energy minimization by dynamic programming is used to detect abrupt changes of motion, called bounces. High-order polynomials are then fitted to smooth trajectory segments between bounces. The output is a continuous trajectory function that assigns location for every real-valued time stamp from zero to the number of frames. The proposed algorithm was evaluated on a newly created dataset of videos from a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms the baselines both in recall and trajectory accuracy. Additionally, we show that from the trajectory function precise physical calculations are possible, such as radius, gravity, and sub-frame object velocity. Velocity estimation is compared to the high-speed camera measurements and radars. Results show high performance of the proposed method in terms of Trajectory-IoU, recall, and velocity estimation. [ABSTRACT FROM AUTHOR]

State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we shift the operating point in this field of conflicts towards universality and speed. Avoiding strong assumptions on the domain or the problem yields a more robust algorithm. This algorithm is fast because we avoid explicit regularization during matching, which allows an efficient computation. Using image information from multiple time steps and explicit visibility prediction based on previous results, we achieve competitive performances on different data sets. Our contributions and results are evaluated in comparative experiments. Overall, we present an accurate scene flow algorithm that is faster and more generic than any individual benchmark leader. [ABSTRACT FROM AUTHOR]

Tracking the head in a video stream is a common thread seen within computer vision literature, supplying the research community with a large number of challenging and interesting problems. Head pose estimation from monocular cameras is often considered an extended application after the face tracking task has already been performed. This often involves passing the resultant 2D data through a simpler algorithm that best fits the data to a static 3D model to determine the 3D pose estimate. This work describes the 2.5D constrained local model, combining a deformable 3D shape point model with 2D texture information to provide direct estimation of the pose parameters, avoiding the need for additional optimization strategies. It achieves this through an analytical derivation of a Jacobian matrix describing how changes in the parameters of the model create changes in the shape within the image through a full-perspective camera model. In addition, the model has very low computational complexity and can run in real-time on modern mobile devices such as tablets and laptops. The point distribution model of the face is built in a unique way, so as to minimize the effect of changes in facial expressions on the estimated head pose and hence make the solution more robust. Finally, the texture information is trained via local neural fields—a deep learning approach that utilizes small discriminative patches to exploit spatial relationships between the pixels and provide strong peaks at the optimal locations. [ABSTRACT FROM AUTHOR]

Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequence. Comparing to landmark-based sparse face shape representation, our method can produce the segmentation masks of individual facial components, which can better reflect their detailed shape variations. By integrating convolutional LSTM (ConvLSTM) algorithm with fully convolutional networks (FCN), our new ConvLSTM-FCN model works on a per-sequence basis and takes advantage of the temporal correlation in video clips. In addition, we also propose a novel loss function, called segmentation loss, to directly optimise the intersection over union (IoU) performances. In practice, to further increase segmentation accuracy, one primary model and two additional models were trained to focus on the face, eyes, and mouth regions, respectively. Our experiment shows the proposed method has achieved a 16.99% relative improvement (from 54.50 to 63.76% mean IoU) over the baseline FCN model on the 300 Videos in the Wild (300VW) dataset. [ABSTRACT FROM AUTHOR]

A novel region-based approach is proposed to find a thin plate spline map between a pair of deformable 3D objects represented by triangular surface meshes. The proposed method works without landmark extraction and feature correspondences. The aligning transformation is simply found by solving a system of integral equations. Each equation is generated by integrating a non-linear function over the object domains. We derive recursive formulas for the efficient computation of these integrals for open and closed surface meshes. Based on a series of comparative tests on a large synthetic dataset, our triangular mesh-based algorithm outperforms state of the art methods both in terms of computing time and accuracy. The applicability of the proposed approach has been demonstrated on the registration of 3D lung CT volumes, brain surfaces and 3D human faces. [ABSTRACT FROM AUTHOR]

We present a novel algorithm for generating the mean structure of non-rigid stretchable shapes. Following an alignment process, which supports local affine deformations, we translate the search of the mean shape into a diagonalization problem where the structure is hidden within the kernel of a matrix. This is the first step required in many practical applications, where one needs to model bendable and stretchable shapes from multiple observations. [ABSTRACT FROM AUTHOR]

We describe an efficient approach to visual object detection that uses short cascades of asymmetric 'one class' classifiers to quickly reject negatives (windows not centered on an object of the desired class) within a sliding window framework. Current detectors typically use binary discriminants such as Support Vector Machines or Boosting to implement each stage of the cascade. These treat the positive and negative classes symmetrically. We argue that this is suboptimal because object detectors typically see a great many negative windows with extremely diverse contents and only a few positive ones with comparatively coherent contents. We show that asymmetric representations that focus on tightly modeling the extent of the rare, coherent positive class can lead to simpler classifiers and faster rejection. Our cascades use asymmetric classifiers based on simple convex models to progressively tighten the bound on the positive class. They typically start with a conventional linear SVM for initial pruning, followed by a cascade of linear distance-to-hyperplane and interior-of-hypersphere classifiers and finishing with a kernelized hypersphere classifier. We show that the resulting detectors have competitive performance on the Labeled Faces in the Wild dataset and state-of-the-art performance on the FDDB face detection, ESOGU face detection and INRIA Person datasets. The results on the PASCAL VOC 2007 dataset are also respectable given that they use neither object parts nor context. The one-class formulations provide significant reductions in classifier complexity relative to the corresponding two-class ones, making them suitable for real-world applications. [ABSTRACT FROM AUTHOR]

Based on an idea in Åström et al. (J Math ImagingVis, doi:, 2017) we propose a new iterative multiplicative filtering algorithm for label assignment matrices which can be used for the supervised partitioning of data. Starting with a row-normalized matrix containing the averaged distances between prior features and observed ones, the method assigns in a very efficient way labels to the data. We interpret the algorithm as a gradient ascent method with respect to a certain function on the product manifold of positive numbers followed by a reprojection onto a subset of the probability simplex consisting of vectors whose components are bounded away from zero by a small constant. While such boundedness away from zero is necessary to avoid an arithmetic underflow, our convergence results imply that they are also necessary for theoretical reasons. Numerical examples show that the proposed simple and fast algorithm leads to very good results. In particular we apply the method for the partitioning of manifold-valued images. [ABSTRACT FROM AUTHOR]

Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure. There is a huge number of transformations to consider but we prove that they can be sampled using a density that depends on the smoothness of the image. For each potential transformation, we approximate the SAD error using a sublinear algorithm that randomly examines only a small number of pixels. We further accelerate the algorithm using a branch-and-bound-like scheme. As images are known to be piecewise smooth, the result is a practical affine template matching algorithm with approximation guarantees, that takes a few seconds to run on a standard machine. We perform several experiments on three different datasets, and report very good results. [ABSTRACT FROM AUTHOR]

We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images. DeepMatching relies on a hierarchical, multi-layer, correlational architecture designed for matching images and was inspired by deep convolutional approaches. The proposed matching algorithm can handle non-rigid deformations and repetitive textures and efficiently determines dense correspondences in the presence of significant changes between images. We evaluate the performance of DeepMatching, in comparison with state-of-the-art matching algorithms, on the Mikolajczyk (Mikolajczyk et al. A comparison of affine region detectors, 2005), the MPI-Sintel (Butler et al. A naturalistic open source movie for optical flow evaluation, 2012) and the Kitti (Geiger et al. Vision meets robotics: The KITTI dataset, 2013) datasets. DeepMatching outperforms the state-of-the-art algorithms and shows excellent results in particular for repetitive textures. We also apply DeepMatching to the computation of optical flow, called DeepFlow, by integrating it in the large displacement optical flow (LDOF) approach of Brox and Malik (Large displacement optical flow: descriptor matching in variational motion estimation, 2011). Additional robustness to large displacements and complex motion is obtained thanks to our matching approach. DeepFlow obtains competitive performance on public benchmarks for optical flow estimation. [ABSTRACT FROM AUTHOR]

We investigate a class of efficient numerical algorithms for many partial differential equations (PDEs) in image analysis. They are applicable to parabolic or elliptic PDEs that have bounded coefficients and lead to space discretisations with symmetric matrices. Our schemes are easy to implement and well-suited for parallel implementations on GPUs, since they are based on the explicit diffusion scheme in the parabolic case, and the Jacobi method in the elliptic case. By supplementing these methods with cyclically varying time step sizes or relaxation parameters, we achieve efficiency gains of several orders of magnitude. We call the resulting algorithms Fast Explicit Diffusion (FED) and Fast Jacobi (FJ) methods. To achieve a good compromise between efficiency and accuracy, we show that one should use parameter cycles that result from factorisations of box filters. For these cycles we establish stability results in the Euclidean norm. Our schemes perform favourably in a number of applications, including isotropic nonlinear diffusion filters with widely varying diffusivities as well as anisotropic diffusion methods for image filtering, inpainting, and regularisation in computer vision. Moreover, they are equally suited for higher dimensional problems as well as higher order PDEs, and they can also be interpreted as efficient first order methods for smooth optimisation problems. [ABSTRACT FROM AUTHOR]

We present an algorithm to reconstruct the 3D trajectory of a moving point from its correspondence in a collection of temporally non-coincidental 2D perspective images, given the time of capture that produced each image and the relative camera poses at each time instant. Triangulation-based solutions do not apply, as multiple views of the point may not exist at each time instant. We represent a 3D trajectory using a linear combination of compact trajectory basis vectors, such as the discrete cosine transform basis, that have been shown to approximate object independence. We note that such basis vectors are also coordinate independent, which allows us to directly use camera poses estimated from stationary areas in the scene (in contrast to nonrigid structure from motion techniques where cameras are simultaneously estimated). This reduces the reconstruction optimization to a linear least squares problem, allowing us to robustly handle missing data that often occur due to motion blur, texture deformation, and self occlusion. We present an algorithm to determine the number of trajectory basis vectors, individually for each trajectory via a cross validation scheme and refine the solution by minimizing the geometric error. The relationship between point and camera motion can cause degeneracies to occur. We geometrically analyze the problem by studying the relationship of the camera motion, point motion, and trajectory basis vectors. We define the reconstructability of a 3D trajectory under projection, and show that the estimate approaches the ground truth when reconstructability approaches infinity. This analysis enables us to precisely characterize cases when accurate reconstruction is achievable. We present qualitative results for the reconstruction of several real-world scenes from a series of 2D projections where high reconstructability can be guaranteed, and report quantitative results on motion capture sequences. [ABSTRACT FROM AUTHOR]

Locally Orderless Tracking (LOT) is a visual tracking algorithm that automatically estimates the amount of local (dis)order in the target. This lets the tracker specialize in both rigid and deformable objects on-line and with no prior assumptions. We provide a probabilistic model of the target variations over time. We then rigorously show that this model is a special case of the Earth Mover's Distance optimization problem where the ground distance is governed by some underlying noise model. This noise model has several parameters that control the cost of moving pixels and changing their color. We develop two such noise models and demonstrate how their parameters can be estimated on-line during tracking to account for the amount of local (dis)order in the target. We also discuss the significance of this on-line parameter update and demonstrate its contribution to the performance. Finally we show LOT's tracking capabilities on challenging video sequences, both commonly used and new, displaying performance comparable to state-of-the-art methods. [ABSTRACT FROM AUTHOR]