CVPR 2017 论文列表

We present a novel approach to noise-blind deblurring, the problem of deblurring an image with known blur, but unknown noise level. We introduce an efficient and robust solution based on a Bayesian framework using a smooth generalization of the 0-1 loss. A novel bound allows the calculation of very high-dimensional integrals in closed form. It avoids the degeneracy of Maximum a-Posteriori (MAP) estimates and leads to an effective noise-adaptive scheme. Moreover, we drastically accelerate our algorithm by using Majorization Minimization (MM) without introducing any approximation or boundary artifacts. We further speed up convergence by turning our algorithm into a neural network termed GradNet, which is highly parallelizable and can be efficiently trained. We demonstrate that our noise-blind formulation can be integrated with different priors and significantly improves existing deblurring algorithms in the noise-blind and in the known-noise case. Furthermore, GradNet leads to state-of-the-art performance across different noise levels, while retaining high computational efficiency.

Depth from focus (DfF) is a method of estimating depth of a scene by using the information acquired through the change of the focus of a camera. Within the framework of DfF, the focus measure (FM) forms the foundation on which the accuracy of the output is determined. With the result from the FM, the role of a DfF pipeline is to determine and recalculate unreliable measurements while enhancing those that are reliable. In this paper, we propose a new FM that more accurately and robustly measures focus, which we call the "ring difference filter" (RDF). FMs can usually be categorized as confident local methods or noise robust non-local methods. RDF's unique ring-and-disk structure allows it to have the advantageous sides of both local and non-local FMs. We then describe an efficient pipeline that utilizes the properties that the RDF brings. Our method is able to reproduce results that are on par with or even better than those of the state-of-the-art, while spending less time in computation.

Linear programming relaxations are central to MAP in- ference in discrete Markov Random Fields. The ability to properly solve the Lagrangian dual is a critical component of such methods. In this paper, we study the benefit of us- ing Newton-type methods to solve the Lagrangian dual of a smooth version of the problem. We investigate their abil- ity to achieve superior convergence behavior and to bet- ter handle the ill-conditioned nature of the formulation, as compared to first order methods. We show that it is indeed possible to efficiently apply a trust region Newton method for a broad range of MAP inference problems. In this pa- per we propose a provably globally efficient framework that includes (i) excellent compromise between computational complexity and precision concerning the Hessian matrix construction, (ii) a damping strategy that aids efficient opti- mization, (iii) a truncation strategy coupled with a generic pre-conditioner for Conjugate Gradients, (iv) efficient sum- product computation for sparse clique potentials. Results for higher-order Markov Random Fields demonstrate the potential of this approach.

e study the problem of holistic scene understanding. We would like to obtain a compact, expressive, and interpretable representation of scenes that encodes information such as the number of objects and their categories, poses, positions, etc. Such a representation would allow us to reason about and even reconstruct or manipulate elements of the scene. Previous works have used encoder-decoder based neural architectures to learn image representations; however, representations obtained in this way are typically uninterpretable, or only explain a single object in the scene. In this work, we propose a new approach to learn an interpretable distributed representation of scenes. Our approach employs a deterministic rendering function as the decoder, mapping a naturally structured and disentangled scene description, which we named scene XML, to an image. By doing so, the encoder is forced to perform the inverse of the rendering operation (a.k.a. de-rendering) to transform an input image to the structured scene XML that the decoder used to produce the image. We use a object proposal based encoder that is trained by minimizing both the supervised prediction and the unsupervised reconstruction errors. Experiments demonstrate that our approach works well on scene de-rendering with two different graphics engines, and our learned representation can be easily adapted for a wide range of applications like image editing, inpainting, visual analogy-making, and image captioning.

Traditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other --- a process that is tedious, fragile, and computationally intensive. In this paper, we propose an end-to-end generative adversarial network that infers a face-specific disentangled representation of intrinsic face properties, including shape (i.e. normals), albedo, and lighting, and an alpha matte. We show that this network can be trained on "in-the-wild" images by incorporating an in-network physically-based image formation module and appropriate loss functions. Our disentangling latent representation allows for semantically relevant edits, where one aspect of facial appearance can be manipulated while keeping orthogonal properties fixed, and we demonstrate its use for a number of facial editing applications.

This paper presents a Neural Aggregation Network (NAN) for video face recognition. The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which maps each face image to a feature vector. The aggregation module consists of two attention blocks which adaptively aggregate the feature vectors to form a single feature inside the convex hull spanned by them. Due to the attention mechanism, the aggregation is invariant to the image order. Our NAN is trained with a standard classification or verification loss without any extra supervision signal, and we found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces. The experiments on IJB-A, YouTube Face, Celebrity-1000 video face recognition benchmarks show that it consistently outperforms naive aggregation methods and achieves the state-of-the-art accuracy.

Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks. However, deep networks are typically resource-intensive and thus difficult to be deployed on mobile devices. Recently, CNNs with binary weights have shown compelling efficiency to the community, whereas the accuracy of such models is usually unsatisfactory in practice. In this paper, we introduce network sketching as a novel technique of pursuing binary-weight CNNs, targeting at more faithful inference and better trade-off for practical applications. Our basic idea is to exploit binary structure directly in pre-trained filter banks and to produce binary-weight models via tensor expansion. The whole process can be treated as a coarse-to-fine model approximation, akin to the pencil drawing steps of outlining and shading. To further speedup the generated models, namely the sketches, we also propose an associative implementation of binary tensor convolutions. Experimental results demonstrate that a proper sketch of AlexNet (or ResNet) outperforms the existing binary-weight models by large margins on the ImageNet large scale classification task, while the committed memory for network parameters only exceeds a little.

We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model, the proposed method draws on a data set of concepts to score the semantics of hidden units at each intermediate convolutional layer. The units with semantics are labeled across a broad range of visual concepts including objects, parts, scenes, textures, materials, and colors. We use the proposed method to test the hypothesis that interpretability is an axis-independent property of the representation space, then we apply the method to compare the latent representations of various networks when trained to solve different classification problems. We further analyze the effect of training iterations, compare networks trained with different initializations, and measure the effect of dropout and batch normalization on the interpretability of deep visual representations. We demonstrate that the proposed method can shed light on characteristics of CNN models and training methods that go beyond measurements of their discriminative power

We propose a direct monocular SLAM algorithm based on the Normalised Information Distance (NID) metric. In contrast to current state-of-the-art direct methods based on photometric error minimisation, our information-theoretic NID metric provides robustness to appearance variation due to lighting, weather and structural changes in the scene. We demonstrate successful localisation and mapping across changes in lighting with a synthetic indoor scene, and across changes in weather (direct sun, rain, snow) using real-world data collected from a vehicle-mounted camera. Our approach runs in real-time on a consumer GPU using OpenGL, and provides comparable localisation accuracy to state-of-the-art photometric methods but significantly outperforms both direct and feature-based methods in robustness to appearance changes.

Scattering effects in images, including those related to haze, fog and appearance of clouds, are fundamentally dictated by microphysical characteristics of the scatterers. This work defines and derives recovery of these characteristics, in a three-dimensional (3D) heterogeneous medium. Recovery is based on a novel tomography approach. Multi-view (multi-angular) and multi-spectral data are linked to the underlying microphysics using 3D radiative transfer, accounting for multiple-scattering. Despite the nonlinearity of the tomography model, inversion is enabled using a few approximations that we describe. As a case study, we focus on passive remote sensing of the atmosphere, where scatterer retrieval can benefit modeling and forecasting of weather, climate and pollution.

Tracking multiple persons in a monocular video of a crowded scene is a challenging task. Humans can master it even if they loose track of a person locally by re-identifying the same person based on their appearance. Care must be taken across long distances, as similar-looking persons need not be identical. In this work, we propose a novel graph-based formulation that links and clusters person hypotheses over time by solving an instance of a minimum cost lifted multicut problem. Our model generalizes previous works by introducing a mechanism for adding long-range attractive connections between nodes in the graph without modifying the original set of feasible solutions. This allows us to reward tracks that assign detections of similar appearance to the same person in a way that does not introduce implausible solutions. To effectively match hypotheses over longer temporal gaps we develop new deep architectures for re-identification of people. They combine holistic representations extracted with deep networks and body pose layout obtained with a state-of-the-art pose estimation model. We demonstrate the effectiveness of our formulation by reporting a new state-of-the-art for the MOT16 benchmark.

Of late, weakly supervised object detection is with great importance in object recognition. Based on deep learning, weakly supervised detectors have achieved many promising results. However, compared with fully supervised detection, it is more challenging to train deep network based detectors in a weakly supervised manner. Here we formulate weakly supervised detection as a Multiple Instance Learning (MIL) problem, where instance classifiers (object detectors) are put into the network as hidden nodes. We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i.e., without object location information. More precisely, instance labels inferred from weak supervision are propagated to their spatially overlapped instances to refine instance classifier online. The iterative instance classifier refinement procedure is implemented using multiple streams in deep network, where each stream supervises its latter stream. Weakly supervised object detection experiments are carried out on the challenging PASCAL VOC 2007 and 2012 benchmarks. We obtain 47% mAP on VOC 2007 that significantly outperforms the previous state-of-the-art.

Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced online iterative optimization, enabling nearly real-time stylization. When those stylization networks are applied directly to high-resolution images, however, the style of localized regions often appears less similar to the desired artistic style. This is because the transfer process fails to capture small, intricate textures and maintain correct texture scales of the artworks. Here we propose a multimodal convolutional neural network that takes into consideration faithful representations of both color and luminance channels, and performs stylization hierarchically with multiple losses of increasing scales. Compared to state-of-the-art networks, our network can also perform style transfer in nearly real-time by performing much more sophisticated training offline. By properly handling style and texture cues at multiple scales using several modalities, we can transfer not just large-scale, obvious style cues but also subtle, exquisite ones. That is, our scheme can generate results that are visually pleasing and more similar to multiple desired artistic styles with color and texture cues at multiple scales.

We propose a multigrid extension of convolutional neural networks (CNNs). Rather than manipulating representations living on a single spatial grid, our network layers operate across scale space, on a pyramid of grids. They consume multigrid inputs and produce multigrid outputs; convolutional filters themselves have both within-scale and cross-scale extent. This aspect is distinct from simple multiscale designs, which only process the input at different scales. Viewed in terms of information flow, a multigrid network passes messages across a spatial pyramid. As a consequence, receptive field size grows exponentially with depth, facilitating rapid integration of context. Most critically, multigrid structure enables networks to learn internal attention and dynamic routing mechanisms, and use them to accomplish tasks on which modern CNNs fail. Experiments demonstrate wide-ranging performance advantages of multigrid. On CIFAR and ImageNet classification tasks, flipping from a single grid to multigrid within the standard CNN paradigm improves accuracy, while being compute and parameter efficient. Multigrid is independent of other architectural choices; we show synergy in combination with residual connections. Multigrid yields dramatic improvement on a synthetic semantic segmentation dataset. Most strikingly, relatively shallow multigrid networks can learn to directly perform spatial transformation tasks, where, in contrast, current CNNs fail. Together, our results suggest that continuous evolution of features on a multigrid pyramid is a more powerful alternative to existing CNN designs on a flat grid.

Owing to prominence as a diagnostic tool for probing the neural correlates of cognition, neuroimaging tensor data has been the focus of intense investigation. Although many supervised tensor learning approaches have been proposed, they either cannot capture the nonlinear relationships of tensor data or cannot preserve the complex multi-way structural information. In this paper, we propose a Multi-way Multi-level Kernel (MMK) model that can extract discriminative, nonlinear and structural preserving representations of tensor data. Specifically, we introduce a kernelized CP tensor factorization technique, which is equivalent to performing the low-rank tensor factorization in a possibly much higher dimensional space that is implicitly defined by the kernel function. We further employ a multi-way nonlinear feature mapping to derive the dual structural preserving kernels, which are used in conjunction with kernel machines (e.g., SVM). Extensive experiments on real-world neuroimages demonstrate that the proposed MMK method can effectively boost the classification performance on diverse brain disorders (i.e., Alzheimer's disease, ADHD, and HIV).

We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view consistency using a differentiable ray consistency (DRC) term. We show that this formulation can be incorporated in a learning framework to leverage different types of multi-view observations e.g. foreground masks, depth, color images, semantics etc. as supervision for learning single-view 3D prediction. We present empirical analysis of our technique in a controlled setting. We also show that this approach allows us to improve over existing techniques for single-view reconstruction of objects from the PASCAL VOC dataset.

This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the bird's eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 14.9% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.

In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different features into account to learn correlation filters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has several advantages. First, it can shepherd the sampled particles toward the modes of the target state distribution via the MCF, thereby resulting in robust tracking performance. Second, it can effectively handle large-scale variation via a particle sampling strategy. Third, it can effectively maintain multiple modes in the posterior density using fewer particles than conventional particle filters, thereby lowering the computational cost. Extensive experimental results on three benchmark datasets demonstrate that the proposed MCPF performs favorably against the state-of-the-art methods.

Sharing information between multiple tasks can enhance the accuracy of human action recognition systems. However, using shared information to improve multi-task human action clustering has never been considered before, and cannot be achieved using existing clustering methods. In this work, we present a novel and effective Multi-Task Information Bottleneck (MTIB) clustering method, which is capable of exploring the shared information between multiple action clustering tasks to improve the performance of individual task. Our motivation is that, different action collections always share many similar action patterns, and exploiting the shared information can lead to improved performance. Specifically, MTIB generally formulates this problem as an information loss minimization function. In this function, the shared information can be quantified by the distributional correlation of clusters in different tasks, which is based on a high-level common vocabulary constructed through a novel agglomerative information maximization method. Extensive experiments on two kinds of challenging data sets, including realistic action data sets (HMDB & UCF50, Olympic & YouTube), and cross-view data sets (IXMAS, WVU), show that the proposed approach compares favorably to the state-of-the-art methods.