Search

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most widely used in the literature due to its strong connection to the human binocular system. Traditionally, stereo-based depth estimation has been addressed through matching hand-crafted features across multiple images. Despite the extensive amount of research, these traditional techniques still suffer in the presence of highly textured areas, large uniform regions, and occlusions. Motivated by their growing success in solving various 2D and 3D vision problems, deep learning for stereo-based depth estimation has attracted a growing interest from the community, with more than 150 papers published in this area between 2014 and 2019. This new generation of methods has demonstrated a significant leap in performance, enabling applications such as autonomous driving and augmented reality. In this paper, we provide a comprehensive survey of this new and continuously growing field of research, summarize the most commonly used pipelines, and discuss their benefits and limitations. In retrospect of what has been achieved so far, we also conjecture what the future may hold for deep learning-based stereo for depth estimation research. [ABSTRACT FROM AUTHOR]

The papers in this special section were presented at the Computer Vision and Pattern Recognition conference. [ABSTRACT FROM AUTHOR]

Recently, a number of empirical studies have compared the performance of PCA and ICA as feature extraction methods in appearance-based object recognition systems, with mixed and seemingly contradictory results. In this paper, we briefly describe the connection between the two methods and argue that whitened PCA may yield identical results to ICA in some cases. Furthermore, we describe the specific situations in which CA might significantly improve on PCA. [ABSTRACT FROM AUTHOR]

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. A list of important papers discussed in this survey, corresponding codes, and additional resources on BLOs are publicly available at: https://github.com/vis-opt-group/BLO. [ABSTRACT FROM AUTHOR]

The papers in this special section were presented at the IEEE Computer Vision and Pattern Recognition (CVPR), June, 2014, jointly sponsored by the IEEE and the Computer Vision Foundation. [ABSTRACT FROM PUBLISHER]

The article offers information related to compact and efficient feature representation and learning in computer vision. It mentions the problems regarding representation and learning of computer vision such as image classification, object recognition, action recognition, and object tracking and also mentions its goal to publish high quality papers that bring a clear picture of the state of the art along this direction.

In this paper, we study the problem of estimating subjective visual properties (SVP) for images, which is an emerging task in Computer Vision. Generally speaking, collecting SVP datasets involves a crowdsourcing process where annotations are obtained from a wide range of online users. Since the process is done without quality control, SVP datasets are known to suffer from noise. This leads to the issue that not all samples are trustworthy. Facing this problem, we need to develop robust models for learning SVP from noisy crowdsourced annotations. In this paper, we construct two general robust learning frameworks for this application. Specifically, in the first framework, we propose a probabilistic framework to explicitly model the sparse unreliable patterns that exist in the dataset. It is noteworthy that we then provide an alternative framework that could reformulate the sparse unreliable patterns as a “contraction” operation over the original loss function. The latter framework leverages not only efficient end-to-end training but also rigorous theoretical analyses. To apply these frameworks, we further provide two models as implementations of the frameworks, where the sparse noise parameters could be interpreted with the HodgeRank theory. Finally, extensive theoretical and empirical studies show the effectiveness of our proposed framework. [ABSTRACT FROM AUTHOR]

An editorial is presented on addressing the need for bringing together leading efforts in non-Euclidean deep learning across all communities. Topics include Convolutional Neural Networks (CNNs) relying on classical signal processing models limiting the applicability to data with underlying Euclidean grid-like structure; and multiple levels of abstraction being introduced similarly to multi-layer networks.

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used datasets for images, videos, audios, and 3D data, as well as the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning. [ABSTRACT FROM AUTHOR]

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-nearest neighbor dynamic time warping (1-NN DTW) and a fully convolutional network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples. [ABSTRACT FROM AUTHOR]

The articles in this special issue include papers from the CVPR'11 conference which was held in Colorado Spring, CO, June 2011. [ABSTRACT FROM PUBLISHER]

Most realtime human pose estimation approaches are based on detecting joint positions. Using the detected joint positions, the yaw and pitch of the limbs can be computed. However, the roll along the limb, which is critical for application such as sports analysis and computer animation, cannot be computed as this axis of rotation remains unobserved. In this paper we therefore introduce orientation keypoints, a novel approach for estimating the full position and rotation of skeletal joints, using only single-frame RGB images. Inspired by how motion-capture systems use a set of point markers to estimate full bone rotations, our method uses virtual markers to generate sufficient information to accurately infer rotations with simple post processing. The rotation predictions improve upon the best reported mean error for joint angles by 48% and achieves 93% accuracy across 15 bone rotations. The method also improves the current state-of-the-art results for joint positions by 14% as measured by MPJPE on the principle dataset, and generalizes well to in-the-wild datasets. [ABSTRACT FROM AUTHOR]

Over the last years, with the advent of Generative Adversarial Networks (GANs), many face analysis tasks have accomplished astounding performance, with applications including, but not limited to, face generation and 3D face reconstruction from a single “in-the-wild” image. Nevertheless, to the best of our knowledge, there is no method which can produce render-ready high-resolution 3D faces from “in-the-wild” images and this can be attributed to the: (a) scarcity of available data for training, and (b) lack of robust methodologies that can successfully be applied on very high-resolution data. In this paper, we introduce the first method that is able to reconstruct photorealistic render-ready 3D facial geometry and BRDF from a single “in-the-wild” image. To achieve this, we capture a large dataset of facial shape and reflectance, which we have made public. Moreover, we define a fast and photorealistic differentiable rendering methodology with accurate facial skin diffuse and specular reflection, self-occlusion and subsurface scattering approximation. With this, we train a network that disentangles the facial diffuse and specular reflectance components from a mesh and texture with baked illumination, scanned or reconstructed with a 3DMM fitting method. As we demonstrate in a series of qualitative and quantitative experiments, our method outperforms the existing arts by a significant margin and reconstructs authentic, 4K by 6K-resolution 3D faces from a single low-resolution image, that are ready to be rendered in various applications and bridge the uncanny valley. [ABSTRACT FROM AUTHOR]

Recognizing wet surfaces and their degrees of wetness is essential for many computer vision applications. Surface wetness can inform us slippery spots on a road to autonomous vehicles, muddy areas of a trail to humanoid robots, and the freshness of groceries to us. The fact that surfaces darken when wet, i.e., monochromatic appearance change, has been modeled to recognize wet surfaces in the past. In this paper, we show that color change, particularly in its spectral behavior, carries rich information about surface wetness. We first derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface. We present a novel method for estimating key parameters of this spectral appearance model, which enables the recovery of the original surface color and the degree of wetness from a single multispectral image. Applied to a multispectral image, the method estimates the spatial map of wetness together with the dry spectral distribution of the surface. To our knowledge, this is the first work to model and leverage the spectral characteristics of wet surfaces to decipher its appearance. We conduct comprehensive experimental validation with a number of wet real surfaces. The results demonstrate the accuracy of our model and the effectiveness of our method for surface wetness and color estimation. [ABSTRACT FROM AUTHOR]

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as “memory” for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a trained model is merely limited to either inference or better initialization towards a target task. In this paper, we go further and extract synthetic data by leveraging the learnt model parameters. We dub them Data Impressions, which act as proxy to the training data and can be used to realize a variety of tasks. These are useful in scenarios where only the pretrained models are available and the training data is not shared (e.g., due to privacy or sensitivity concerns). We show the applicability of data impressions in solving several computer vision tasks such as unsupervised domain adaptation, continual learning as well as knowledge distillation. We also study the adversarial robustness of lightweight models trained via knowledge distillation using these data impressions. Further, we demonstrate the efficacy of data impressions in generating data-free Universal Adversarial Perturbations (UAPs) with better fooling rates. Extensive experiments performed on benchmark datasets demonstrate competitive performance achieved using data impressions in absence of original training data. [ABSTRACT FROM AUTHOR]

Deep neural networks have been tremendously successful at segmenting objects in images. However, it has been shown they still have limitations on challenging problems such as the segmentation of medical images. The main reason behind this lower success resides in the reduced size of the object in the image. In this paper we overcome this limitation through a cyclic collaborative framework, CyCoSeg. The proposed framework is based on a deep active shape model (D-ASM), which provides prior information about the shape of the object, and a semantic segmentation network (SSN). These two models collaborate to reach the desired segmentation by influencing each other: SSN helps D-ASM identify relevant keypoints in the image through an Expectation Maximization formulation, while D-ASM provides a segmentation proposal that guides the SSN. This cycle is repeated until both models converge. Extensive experimental evaluation shows CyCoSeg boosts the performance of the baseline models, including several popular SSNs, while avoiding major architectural modifications. The effectiveness of our method is demonstrated on the left ventricle segmentation on two benchmark datasets, where our approach achieves one of the most competitive results in segmentation accuracy. Furthermore, its generalization is demonstrated for lungs and kidneys segmentation in CT scans. [ABSTRACT FROM AUTHOR]

Hypergraph matching has recently become a popular approach for solving correspondence problems in computer vision as it allows the use of higher-order geometric information. Hypergraph matching can be formulated as a third-order optimization problem subject to assignment constraints which turns out to be NP-hard. In recent work, we have proposed an algorithm for hypergraph matching which first lifts the third-order problem to a fourth-order problem and then solves the fourth-order problem via optimization of the corresponding multilinear form. This leads to a tensor block coordinate ascent scheme which has the guarantee of providing monotonic ascent in the original matching score function and leads to state-of-the-art performance both in terms of achieved matching score and accuracy. In this paper we show that the lifting step to a fourth-order problem can be avoided yielding a third-order scheme with the same guarantees and performance but being two times faster. Moreover, we introduce a homotopy type method which further improves the performance. [ABSTRACT FROM AUTHOR]

Estimating the pose of a calibrated camera relative to a 3D point set from one image is an important task in computer vision. Perspective-n-Point algorithms are often used if perfect 2D-3D correspondences are known. However, it is difficult to determine 2D-3D correspondences perfectly, and then the simultaneous pose and correspondence determination problem is needed to be solved. Early methods aimed to solve this problem by local optimization. Recently, several new methods are proposed to globally solve this problem by using branch-and-bound (BnB) method, but they tend to be slow because the time complexity of the BnB-based methods is exponential to the dimensionality of the parameter space, and they directly search the 6D parameter space. In this paper, we propose to decompose the joint searching into two separate searching processes by introducing a rotation invariant feature (RIF). Specifically, we construct RIFs from the original 3D and 2D point sets and search for the globally optimal translation to match these two RIFs first. Then, the original 3D point set is translated and matched with the 2D point set to find a globally optimal rotation. Experiments on challenging data show that the proposed method outperforms state-of-the-art methods in terms of both speed and accuracy. [ABSTRACT FROM AUTHOR]

Image smoothing is a fundamental procedure in applications of both computer vision and graphics. The required smoothing properties can be different or even contradictive among different tasks. Nevertheless, the inherent smoothing nature of one smoothing operator is usually fixed and thus cannot meet the various requirements of different applications. In this paper, we first introduce the truncated Huber penalty function which shows strong flexibility under different parameter settings. A generalized framework is then proposed with the introduced truncated Huber penalty function. When combined with its strong flexibility, our framework is able to achieve diverse smoothing natures where contradictive smoothing behaviors can even be achieved. It can also yield the smoothing behavior that can seldom be achieved by previous methods, and superior performance is thus achieved in challenging cases. These together enable our framework capable of a range of applications and able to outperform the state-of-the-art approaches in several tasks, such as image detail enhancement, clip-art compression artifacts removal, guided depth map restoration, image texture removal, etc. In addition, an efficient numerical solution is provided and its convergence is theoretically guaranteed even the optimization framework is non-convex and non-smooth. A simple yet effective approach is further proposed to reduce the computational cost of our method while maintaining its performance. The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications. Our code is available at https://github.com/wliusjtu/Generalized-Smoothing-Framework . [ABSTRACT FROM AUTHOR]

In this paper, we consider how to incorporate psychophysical measurements of human visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can reduce errors. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century. [ABSTRACT FROM AUTHOR]

Cameras currently allow access to two image states: (i) a minimally processed linear raw-RGB image state (i.e., raw sensor data); or (ii) a highly-processed nonlinear image state (e.g., sRGB). There are many computer vision tasks that work best with a linear image state, such as image deblurring and image dehazing. Unfortunately, the vast majority of images are saved in the nonlinear image state. Because of this, a number of methods have been proposed to “unprocess” nonlinear images back to a raw-RGB state. However, existing unprocessing methods have a drawback because raw-RGB images are sensor-specific. As a result, it is necessary to know which camera produced the sRGB output and use a method or network tailored for that sensor to properly unprocess it. This paper addresses this limitation by exploiting another camera image state that is not available as an output, but it is available inside the camera pipeline. In particular, cameras apply a colorimetric conversion step to convert the raw-RGB image to a device-independent space based on the CIE XYZ color space before they apply the nonlinear photo-finishing. Leveraging this canonical image state, we propose a deep learning framework, CIE XYZ Net, that can unprocess a nonlinear image back to the canonical CIE XYZ image. This image can then be processed by any low-level computer vision operator and re-rendered back to the nonlinear image. We demonstrate the usefulness of the CIE XYZ Net on several low-level vision tasks and show significant gains that can be obtained by this processing framework. Code and dataset are publicly available at https://github.com/mahmoudnafifi/CIE_XYZ_NET. [ABSTRACT FROM AUTHOR]

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $\Pi$ Π -Nets, a new class of function approximators based on polynomial expansions. $\Pi$ Π -Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that $\Pi$ Π -Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, $\Pi$ Π -Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets. [ABSTRACT FROM AUTHOR]

This special section contains selected papers from the IEEE Computer Vision and Pattern Recognition (CVPR), June, 2013, jointly sponsored by the IEEE and the Computer Vision Foundation. [ABSTRACT FROM PUBLISHER]

Finding the informative subspaces of high-dimensional datasets is at the core of numerous applications in computer vision, where spectral-based subspace clustering is arguably the most widely studied method due to its strong empirical performance. Such algorithms first compute an affinity matrix to construct a self-representation for each sample using other samples as a dictionary. Sparsity and connectivity of the self-representation play important roles in effective subspace clustering. However, simultaneous optimization of both factors is difficult due to their conflicting nature, and most existing methods are designed to address only one factor. In this paper, we propose a post-processing technique to optimize both sparsity and connectivity by finding good neighbors. Good neighbors induce key connections among samples within a subspace and not only have large affinity coefficients but are also strongly connected to each other. We reassign the coefficients of the good neighbors and eliminate other entries to generate a new coefficient matrix. We show that the few good neighbors can effectively recover the subspace, and the proposed post-processing step of finding good neighbors is complementary to most existing subspace clustering algorithms. Experiments on five benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods with negligible additional computation cost. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses appointment of several associate editors in the periodical's editorial board including Amr Ahmed, Xiang Bai, and Dima Damen.

While the detection of the interesting regions in images has been extensively studied, relatively few papers have addressed surfaces. This paper proposes an algorithm for detecting the regions of interest of surfaces. It looks for regions that are distinct both locally and globally and accounts for the distance to the foci of attention. It is also shown how this algorithm can be adopted to saliency detection in point clouds. Many applications can utilize these regions. In this paper we explore one such application—viewpoint selection. The most informative views are those that collectively provide the most descriptive presentation of the surface. We show that our results compete favorably with the state-of-the-art results. [ABSTRACT FROM AUTHOR]

Dynamic vision sensors (event cameras) have recently been introduced to solve a number of different vision tasks such as object recognition, activities recognition, tracking, etc. Compared with the traditional RGB sensors, the event cameras have many unique advantages such as ultra low resources consumption, high temporal resolution and much larger dynamic range. However, these cameras only produce noisy and asynchronous events of intensity changes, i.e., event-streams rather than frames, where conventional computer vision algorithms can't be directly applied. In our opinion the key challenge for improving the performance of event cameras in vision tasks is finding the appropriate representations of the event-streams so that cutting-edge learning approaches can be applied to fully uncover the spatio-temporal information contained in the event-streams. In this paper, we focus on the event-based human gait identification task and investigate the possible representations of the event-streams when deep neural networks are applied as the classifier. We propose new event-based gait recognition approaches basing on two different representations of the event-stream, i.e., graph and image-like representations, and use graph-based convolutional network (GCN) and convolutional neural networks (CNN) respectively to recognize gait from the event-streams. The two approaches are termed as EV-Gait-3DGraph and EV-Gait-IMG. To evaluate the performance of the proposed approaches, we collect two event-based gait datasets, one from real-world experiments and the other by converting the publicly available RGB gait recognition benchmark CASIA-B. Extensive experiments show that EV-Gait-3DGraph achieves significantly higher recognition accuracy than other competing methods when sufficient training samples are available. However, EV-Gait-IMG converges more quickly than graph-based approaches while training and shows good accuracy with only few number of training samples (less than ten). So image-like presentation is preferable when the amount of training data is limited. [ABSTRACT FROM AUTHOR]

In recent years, weakly supervised object detection has attracted great attention in the computer vision community. Although numerous deep learning-based approaches have been proposed in the past few years, such an ill-posed problem is still challenging and the learning performance is still behind the expectation. In fact, most of the existing approaches only consider the visual appearance of each proposal region but ignore to make use of the helpful context information. To this end, this paper introduces two levels of context into the weakly supervised learning framework. The first one is the proposal-level context, i.e., the relationship of the spatially adjacent proposals. The second one is the semantic-level context, i.e., the relationship of the co-occurring object categories. Therefore, the proposed weakly supervised learning framework contains not only the cognition process on the visual appearance but also the reasoning process on the proposal- and semantic-level relationships, which leads to the novel deep multiple instance reasoning framework. Specifically, built upon a conventional CNN-based network architecture, the proposed framework is equipped with two additional graph convolutional network-based reasoning models to implement object location reasoning and multi-label reasoning within an end-to-end network training procedure. Comprehensive experiments on the widely used PASCAL VOC and MS COCO benchmarks have been implemented, which demonstrate the superior capacity of the proposed approach when compared with other state-of-the-art methods and baseline models. [ABSTRACT FROM AUTHOR]

Finding relative pose between two calibrated images is a fundamental task in computer vision. Given five point correspondences, the classical five-point methods can be used to calculate the essential matrix efficiently. For the case of $N$ N ($N > 5$ N > 5 ) inlier point correspondences, which is called $N$ N -point problem, existing methods are either inefficient or prone to local minima. In this paper, we propose a certifiably globally optimal and efficient solver for the $N$ N -point problem. First we formulate the problem as a quadratically constrained quadratic program (QCQP). Then a certifiably globally optimal solution to this problem is obtained by semidefinite relaxation. This allows us to obtain certifiably globally optimal solutions to the original non-convex QCQPs in polynomial time. The theoretical guarantees of the semidefinite relaxation are also provided, including tightness and local stability. To deal with outliers, we propose a robust $N$ N -point method using M-estimators. Though global optimality cannot be guaranteed for the overall robust framework, the proposed robust $N$ N -point method can achieve good performance when the outlier ratio is not high. Extensive experiments on synthetic and real-world datasets demonstrated that our $N$ N -point method is $2\sim 3$ 2 ∼ 3 orders of magnitude faster than state-of-the-art methods. Moreover, our robust $N$ N -point method outperforms state-of-the-art methods in terms of robustness and accuracy. [ABSTRACT FROM AUTHOR]

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramid×pyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios. [ABSTRACT FROM AUTHOR]

Geometric deep learning is a relatively nascent field that has attracted significant attention in the past few years. This is partly due to the availability of data acquired from non-euclidean domains or features extracted from euclidean-space data that reside on smooth manifolds. For instance, pose data commonly encountered in computer vision reside in Lie groups, while covariance matrices that are ubiquitous in many fields and diffusion tensors encountered in medical imaging domain reside on the manifold of symmetric positive definite matrices. Much of this data is naturally represented as a grid of manifold-valued data. In this paper we present a novel theoretical framework for developing deep neural networks to cope with these grids of manifold-valued data inputs. We also present a novel architecture to realize this theory and call it the ManifoldNet. Analogous to vector spaces where convolutions are equivalent to computing weighted sums, manifold-valued data ‘convolutions’ can be defined using the weighted Fréchet Mean (${\sf wFM}$ wFM ). (This requires endowing the manifold with a Riemannian structure if it did not already come with one.) The hidden layers of ManifoldNet compute ${\sf wFM}$ wFM s of their inputs, where the weights are to be learnt. This means the data remain manifold-valued as they propagate through the hidden layers. To reduce computational complexity, we present a provably convergent recursive algorithm for computing the ${\sf wFM}$ wFM . Further, we prove that on non-constant sectional curvature manifolds, each ${\sf wFM}$ wFM layer is a contraction mapping and provide constructive evidence for its non-collapsibility when stacked in layers. This captures the two fundamental properties of deep network layers. Analogous to the equivariance of convolution in euclidean space to translations, we prove that the ${\sf wFM}$ wFM is equivariant to the action of the group of isometries admitted by the Riemannian manifold on which the data reside. To showcase the performance of ManifoldNet, we present several experiments using both computer vision and medical imaging data sets. [ABSTRACT FROM AUTHOR]

Standard edge detection operators such as the Laplacian of Gaussian and the gradient of Gaussian can be used to track contours in image sequences. When using edge operators, a contour, which is determined on a frame of the sequence, is simply used as a starting contour to locate the nearest contour on the subsequent frame. However, the strategy used to look for the nearest edge points may not work when tracking contours of non isolated gray level discontinuities. In these cases, strategies derived from the optical flow equation, which look for similar gray level distributions, appear to be more appropriate since these can work with a lower frame rate than that needed for strategies based on pure edge detection operators. However, an optical flow strategy tends to propagate the localization errors through the sequence and an additional edge detection procedure is essential to compensate for such a drawback. In this paper a spatio-temporal intensity moment is proposed which integrates the two basic functions of edge detection and tracking. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a family of graph partition similarity measures that take the topology of the graph into account. These graph-aware measures are alternatives to using set partition similarity measures that are not specifically designed for graphs. The two types of measures, graph-aware and set partition measures, are shown to have opposite behaviors with respect to resolution issues and provide complementary information necessary to compare graph partitions. [ABSTRACT FROM AUTHOR]

Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the deep representations in the hyperbolic space provide high fidelity embeddings with few dimensions, especially for data possessing hierarchical structure. Such a hyperbolic neural architecture is quickly extended to different scientific fields, including natural language processing, single-cell RNA-sequence analysis, graph embedding, financial analysis, and computer vision. The promising results demonstrate its superior capability, significant compactness of the model, and a substantially better physical interpretability than its counterpart in the euclidean space. To stimulate future research, this paper presents a comprehensive review of the literature around the neural components in the construction of HDNN, as well as the generalization of the leading deep approaches to the hyperbolic space. It also presents current applications of various tasks, together with insightful observations and identifying open questions and promising future directions. [ABSTRACT FROM AUTHOR]

There have been a number of corner detection methods proposed for event cameras in the last years, since event-driven computer vision has become more accessible. Current state-of-the-art have either unsatisfactory accuracy or real-time performance when considered for practical use, for example when a camera is randomly moved in an unconstrained environment. In this paper, we present yet another method to perform corner detection, dubbed look-up event-Harris (luvHarris), that employs the Harris algorithm for high accuracy but manages an improved event throughput. Our method has two major contributions, 1. a novel “threshold ordinal event-surface” that removes certain tuning parameters and is well suited for Harris operations, and 2. an implementation of the Harris algorithm such that the computational load per event is minimised and computational heavy convolutions are performed only ‘as-fast-as-possible’, i.e., only as computational resources are available. The result is a practical, real-time, and robust corner detector that runs more than $2.6\times$ 2. 6 × the speed of current state-of-the-art; a necessity when using a high-resolution event-camera in real-time. We explain the considerations taken for the approach, compare the algorithm to current state-of-the-art in terms of computational performance and detection accuracy, and discuss the validity of the proposed approach for event cameras. [ABSTRACT FROM AUTHOR]

Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. The topic attracts increased attention with the emerging pipeline of deep learning surface reconstruction, where implicit field functions constructed from deep networks (e.g., multi-layer perceptrons or MLPs) are proposed for generative shape modeling. In this paper, we study a fundamental problem in this context about recovering a surface mesh from an implicit field function whose zero-level set captures the underlying surface. To achieve the goal, existing methods rely on traditional meshing algorithms (e.g., the de-facto standard marching cubes); while promising, they suffer from loss of precision learned in the implicit surface networks, due to the use of discrete space sampling in marching cubes. Given that an MLP with activations of Rectified Linear Unit (ReLU) partitions its input space into a number of linear regions, we are motivated to connect this local linearity with a same property owned by the desired result of polygon mesh. More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic facesthat are associated with the function's zero-level isosurface. We prove that under mild conditions, the identified analytic faces are guaranteed to connect and form a closed, piecewise planar surface. Based on the theorem, we propose an algorithm of analytic marching, which marches among analytic cells to exactly recover the mesh captured by an implicit surface network. We also show that our theory and algorithm are equally applicable to advanced MLPs with shortcut connections and max pooling. Given the parallel nature of analytic marching, we contribute AnalyticMesh, a software package that supports efficient meshing of implicit surface networks via CUDA parallel computing, and mesh simplification for efficient downstream processing. We apply our method to different settings of generative shape modeling using implicit surface networks. Extensive experiments demonstrate our advantages over existing methods in terms of both meshing accuracy and efficiency. Codes are at https://github.com/Karbo123/AnalyticMesh. [ABSTRACT FROM AUTHOR]

Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art computer vision models, i.e., pre-training a model for image classification on the ILSVRC dataset, and then fine-tune on any target task. However, previous systematic studies of transfer learning have been limited and the circumstances in which it is expected to work are not fully understood. In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains (consumer photos, autonomous driving, aerial imagery, underwater, indoor scenes, synthetic, close-ups) and task types (semantic segmentation, object detection, depth estimation, keypoint detection). Importantly, these are all complex, structured output tasks types relevant to modern computer vision applications. In total we carry out over 2000 transfer learning experiments, including many where the source and target come from different image domains, task types, or both. We systematically analyze these experiments to understand the impact of image domain, task type, and dataset size on transfer learning performance. Our study leads to several insights and concrete recommendations: (1) for most tasks there exists a source which significantly outperforms ILSVRC’12 pre-training; (2) the image domain is the most important factor for achieving positive transfer; (3) the source dataset should include the image domain of the target dataset to achieve best results; (4) at the same time, we observe only small negative effects when the image domain of the source task is much broader than that of the target; (5) transfer across task types can be beneficial, but its success is heavily dependent on both the source and target task types. [ABSTRACT FROM AUTHOR]

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset. [ABSTRACT FROM AUTHOR]

Intrinsic image decomposition is the task of mapping image to albedo and shading. Classical approaches derive methods from spatial models. The modern literature stresses evaluation, by comparing predictions to human judgements (“lighter”, “same as”, “darker”). The best modern intrinsic image methods train a map from image to albedo using images rendered from computer graphics models and example human judgements. This approach yields practical methods, but obtaining rendered images can be inconvenient. Furthermore, the approach cannot explain how a one could learn to recover intrinsic images without geometric, surface and illumination models, as people and animals appear to do. This paper describes a method that learns intrinsic image decomposition without seeing human annotations, rendered data, or ground truth data. Instead, the method relies on paradigms – spatial models of albedo and of shading. Rather than finding the “best” albedo and shading for an image via optimization, our approach trains a neural network on synthetic images. The synthetic images are constructed by multiplying albedos and shading fields sampled from our models. The network is subject to a novel smoothing procedure that ensures good behavior at short scales on real images. An averaging procedure ensures that reported albedo and shading are largely equivariant – different crops and scalings of an image will report the same albedo and shading at shared points. This averaging procedure controls long scale error. The standard evaluation for an intrinsic image method is a WHDR score. Our method achieves WHDR scores competitive with those of strong recent methods allowed to see training WHDR annotations, rendered data, and ground truth data. Our method produces albedo and shading maps with attractive qualitative properties – for example, albedo fields do not suppress wood grain and represent narrow grooves in surfaces well. Because our method is unsupervised, we can compute estimates of the test/train variance of WHDR scores; these are quite large, and suggest is unsafe to rely small differences in reported WHDR. [ABSTRACT FROM AUTHOR]

The skeleton of a 2D shape is an important geometric structure in pattern analysis and computer vision. In this paper we study the skeleton of a 2D shape in a two-manifold \mathcal M , based on a geodesic metric. We present a formal definition of the skeleton $S(\Omega )$ for a shape \Omega$ in S(\Omega )$ distinct from its Euclidean counterpart in . We further prove that for a shape sequence \lbrace \Omega _i\rbrace$ that converge to a shape \Omega$ in \mathcal M , the mapping is lower semi-continuous. A direct application of this result is that we can use a set P$ of sample points to approximate the boundary of a 2D shape \Omega$ in P gives a good approximation to the skeleton $S(\Omega )$ . Examples of skeleton computation in topography and brain morphometry are illustrated. [ABSTRACT FROM AUTHOR]

In many computer vision applications, a desired model of some type is computed by minimizing a cost function based on several measurements. Typically, one may compute the model that minimizes the $L_2$ cost, that is the sum of squares of measurement errors with respect to the model. However, the $Lq$ solution which minimizes the sum of the $q$ th power of errors usually gives more robust results in the presence of outliers for some values of $q$ , for example, $q = 1$ . The Weiszfeld algorithm is a classic algorithm for finding the geometric $L1$ mean of a set of points in Euclidean space. It is provably optimal and requires neither differentiation, nor line search. The Weiszfeld algorithm has also been generalized to find the $L1$ mean of a set of points on a Riemannian manifold of non-negative curvature. This paper shows that the Weiszfeld approach may be extended to a wide variety of problems to find an $Lq$ mean for $1\le q \lt 2$ , while maintaining simplicity and provable convergence. We apply this problem to both single-rotation averaging (under which the algorithm provably finds the global $Lq$ optimum) and multiple rotation averaging (for which no such proof exists). Experimental results of $Lq$ optimization for rotations show the improved reliability and robustness compared to $L_2$ optimization. [ABSTRACT FROM PUBLISHER]

An editorial is presented on standard supervised image classification becoming increasingly practical and fine-grained visual categorization (FGVC). Topics include research works follow the state-of-the-art general-purpose image classification approaches directly applying deep neural networks to FGVC tasks; and datasets showing the effectiveness of the proposed approach and one-shot learning ability and scalability.

The understanding of the mechanisms behind focus of attention in a visual scene is a problem of great interest in visual perception and computer vision. In this paper, we describe a model of scanpath as a dynamic process which can be interpreted as a variational law somehow related to mechanics, where the focus of attention is subject to a gravitational field. The distributed virtual mass that drives eye movements is associated with the presence of details and motion in the video. Unlike most current models, the proposed approach does not estimate directly the saliency map, but the prediction of eye movements allows us to integrate over time the positions of interest. The process of inhibition-of-return is also supported in the same dynamic model with the purpose of simulating fixations and saccades. The differential equations of motion of the proposed model are numerically integrated to simulate scanpaths on both images and videos. Experimental results for the tasks of saliency and scanpath prediction on a wide collection of datasets are presented to support the theory. Top level performances are achieved especially in the prediction of scanpaths, which is the primary purpose of the proposed model. [ABSTRACT FROM AUTHOR]

Nearest neighbor search is a fundamental problem in computer vision and machine learning. The straightforward solution, linear scan, is both computationally and memory intensive in large scale high-dimensional cases, hence is not preferable in practice. Therefore, there have been a lot of interests in algorithms that perform approximate nearest neighbor (ANN) search. In this paper, we propose a novel addition-based vector quantization algorithm, Asymmetric Mapping Quantization (AMQ), to efficiently conduct ANN search. Unlike existing addition-based quantization methods that suffer from handling the problem caused by the norm of database vector, we map the query vector and database vector using different mapping functions to transform the computation of L-2 distance to inner product similarity, thus do not need to evaluate the norm of database vector. Moreover, we further propose Distributed Asymmetric Mapping Quantization (DAMQ) to enable AMQ to work on very large dataset by distributed learning. Extensive experiments on approximate nearest neighbor search and image retrieval validate the merits of the proposed AMQ and DAMQ. [ABSTRACT FROM AUTHOR]

Recovering the shape and reflectance of non-Lambertian surfaces remains a challenging problem in computer vision since the view-dependent appearance invalidates traditional photo-consistency constraint. In this paper, we introduce a novel concentric multi-spectral light field (CMSLF) design that is able to recover the shape and reflectance of surfaces of various materials in one shot. Our CMSLF system consists of an array of cameras arranged on concentric circles where each ring captures a specific spectrum. Coupled with a multi-spectral ring light, we are able to sample viewpoint and lighting variations in a single shot via spectral multiplexing. We further show that our concentric camera and light source setting results in a unique single-peak pattern in specularity variations across viewpoints. This property enables robust depth estimation for specular points. To estimate depth and multi-spectral reflectance map, we formulate a physics-based reflectance model for the CMSLF under the surface camera (S-Cam) representation. Extensive synthetic and real experiments show that our method outperforms the state-of-the-art shape reconstruction methods, especially for non-Lambertian surfaces. [ABSTRACT FROM AUTHOR]

Accurate and efficient methods for large-scale urban reconstruction are of significant importance to the computer vision and computer graphics communities. Although rapid acquisition techniques such as airborne LiDAR have been around for many years, creating a useful and functional virtual environment from such data remains difficult and labor intensive. This is due largely to the necessity in present solutions for data dependent user defined parameters. In this paper we present a new solution for automatically converting large LiDAR data pointcloud into simplified polygonal 3D models. The data is first divided into smaller components which are processed independently and concurrently to extract various metrics about the points. Next, the extracted information is converted into tensors. A robust agglomerate clustering algorithm is proposed to segment the tensors into clusters representing geospatial objects e.g., roads, buildings, etc. Unlike previous methods, the proposed tensor clustering process has no data dependencies and does not require any user-defined parameter. The required parameters are adaptively computed assuming a Weibull distribution for similarity distances. Lastly, to extract boundaries from the clusters a new multi-stage boundary refinement process is developed by reformulating this extraction as a global optimization problem. We have extensively tested our methods on several pointcloud datasets of different resolutions which exhibit significant variability in geospatial characteristics e.g., ground surface inclination, building density, etc and the results are reported. The source code for both tensor clustering and global boundary refinement will be made publicly available with the publication on the author's website. [ABSTRACT FROM AUTHOR]

End-to-end distance metric learning (DML) has been applied to obtain features useful in many computer vision tasks. However, these DML studies have not provided equitable comparisons between features extracted from DML-based networks and softmax-based networks. In this paper, we present objective comparisons between these two approaches under the same network architecture. [ABSTRACT FROM AUTHOR]

Light field imaging has recently known a regain of interest due to the availability of practical light field capturing systems that offer a wide range of applications in the field of computer vision. However, capturing high-resolution light fields remains technologically challenging since the increase in angular resolution is often accompanied by a significant reduction in spatial resolution. This paper describes a learning-based spatial light field super-resolution method that allows the restoration of the entire light field with consistency across all angular views. The algorithm first uses optical flow to align the light field and then reduces its angular dimension using low-rank approximation. We then consider the linearly independent columns of the resulting low-rank model as an embedding, which is restored using a deep convolutional neural network (DCNN). The super-resolved embedding is then used to reconstruct the remaining views. The original disparities are restored using inverse warping where missing pixels are approximated using a novel light field inpainting algorithm. Experimental results show that the proposed method outperforms existing light field super-resolution algorithms, achieving PSNR gains of 0.23 dB over the second best performing method. The performance is shown to be further improved using iterative back-projection as a post-processing step. [ABSTRACT FROM AUTHOR]