CVPR 2018 论文列表

We introduce a seemingly impossible task: given only an audio clip of someone speaking, decide which of two face images is the speaker. In this paper we study this, and a number of related cross-modal tasks, aimed at answering the question: how much can we infer from the voice about the face and vice versa? We study this task “in the wild”, employing the datasets that are now publicly available for face recognition from static images (VGGFace) and speaker identification from audio (VoxCeleb). These provide training and testing scenarios for both static and dynamic testing of cross-modal matching. We make the following contributions: (i) we introduce CNN architectures for both binary and multi-way cross-modal face and audio matching; (ii) we compare dynamic testing (where video information is available, but the audio is not from the same video) with static testing (where only a single still image is available); and (iii) we use hu- man testing as a baseline to calibrate the difficulty of the task. We show that a CNN can indeed be trained to solve this task in both the static and dynamic scenarios, and is even well above chance on 10-way classification of the face given the voice. The CNN matches human performance on easy examples (e.g. different gender across faces) but exceeds human performance on more challenging examples (e.g. faces with the same gender, age and nationality).

In this paper, we propose a novel method for measuring the temporal modulation of lights by using off-the-shelf cameras. In particular, we show that the invisible flicker patterns of various lights such as fluorescent lights can be measured by a simple combination of an off-the-shelf camera and any moving object with specular reflection. Unlike the existing methods, we do not need high speed cameras nor specially designed coded exposure cameras. Based on the extracted flicker patterns of environment lights, we also propose an efficient method for deblurring motion blurs in images. The proposed method enables us to deblur images with better frequency characteristics, which are induced by the flicker patterns of environment lights. The real image experiments show the efficiency of the proposed method.

This paper introduces a novel anchor design principle to support anchor-based face detection for superior scale-invariant performance, especially on tiny faces. To achieve this, we explicitly address the problem that anchor-based detectors drop performance drastically on faces with tiny sizes, e.g. less than 16x16 pixels. In this paper, we investigate why this is the case. We discover that current anchor design cannot guarantee high overlaps between tiny faces and anchor boxes, which increases the difficulty of training. The new Expected Max Overlapping (EMO) score is proposed which can theoretically explain the low overlapping issue and inspire several effective strategies of new anchor design leading to higher face overlaps, including anchor stride reduction with new network architectures, extra shifted anchors, and stochastic face shifting. Comprehensive experiments show that our proposed method significantly outperforms the baseline anchor-based detector, while consistently achieving state-of-the-art results on challenging face detection datasets with competitive runtime speed.

In this paper, we propose an automatic seed generation technique with deep reinforcement learning to solve the interactive segmentation problem. One of the main issues of the interactive segmentation problem is robust and consistent object extraction with less human effort. Most of the existing algorithms highly depend on the distribution of inputs, which differs from one user to another and hence need sequential user interactions to achieve adequate performance. In our system, when a user first specifies a point on the desired object and a point in the background, a sequence of artificial user input is automatically generated for precisely segmenting the desired object. The proposed system allows the user to reduce the number of input significantly. This problem is difficult to cast as a supervised learning problem because it is not possible to define globally optimal user input at some stage of the interactive segmentation task. Hence, we formulate automatic seed generation problem as Markov Decision Process (MDP) and then optimize it by reinforcement learning with Deep Q-Network (DQN). We train our network on the MSRA10K dataset and show that the network achieves notable performance improvement from inaccurate initial segmentation on both seen and unseen datasets.

Objects often occlude each other in scenes; Inferring their appearance beyond their visible parts plays an important role in scene understanding, depth estimation, object interaction and manipulation. In this paper, we study the challenging problem of completing the appearance of occluded objects. Doing so requires knowing which pixels to paint (segmenting the invisible parts of objects) and what color to paint them (generating the invisible parts). Our proposed novel solution, SeGAN, jointly optimizes for both segmentation and generation of the invisible parts of objects. Our experimental results show that: (a) SeGAN can learn to generate the appearance of the occluded parts of objects; (b) SeGAN outperforms state-of-the-art segmentation baselines for the invisible parts of objects; (c) trained on synthetic photo realistic images, SeGAN can reliably segment natural images; (d) by reasoning about occluder-occludee relations, our method can infer depth layering.

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to handle large scenes with varying spatial extent, managing the cubic growth in data size as scene size increases. To this end, we devise a fully-convolutional generative 3D CNN model whose filter kernels are invariant to the overall scene size. The model can be trained on scene subvolumes but deployed on arbitrarily large scenes at test time. In addition, we propose a coarse-to-fine inference strategy in order to produce high-resolution output while also leveraging large input context sizes. In an extensive series of experiments, we carefully evaluate different model design choices, considering both deterministic and probabilistic models for completion and semantic inference. Our results show that we outperform other methods not only in the size of the environments handled and processing efficiency, but also with regard to completion quality and semantic segmentation performance by a significant margin.

Scale problem lies in the heart of object detection. In this work, we develop a novel Scale-Transferrable Detection Network (STDN) for detecting multi-scale objects in images. In contrast to previous methods that simply combine object predictions from multiple feature maps from different network depths, the proposed network is equipped with embedded super-resolution layers (named as scale-transfer layer/module in this work) to explicitly explore the inter-scale consistency nature across multiple detection scales. Scale-transfer module naturally fits the base network with little computational cost. This module is further integrated with a dense convolutional network (DenseNet) to yield a one-stage object detector. We evaluate our proposed architecture on PASCAL VOC 2007 and MS COCO benchmark tasks and STDN obtains significant improvements over the comparable state-of-the-art detection models.

In single image deblurring, the ``coarse-to-fine'' scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many recent learning-based approaches, it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-the-arts, both quantitatively and qualitatively.

Recently the widely used multi-view learning model, Canonical Correlation Analysis (CCA) has been generalised to the non-linear setting via deep neural networks. Existing deep CCA models typically first decorrelate the feature dimensions of each view before the different views are maximally correlated in a common latent space. This feature decorrelation is achieved by enforcing an exact decorrelation constraint; these models are thus computationally expensive due to the matrix inversion or SVD operations required for exact decorrelation at each training iteration. Furthermore, the decorrelation step is often separated from the gradient descent based optimisation, resulting in sub-optimal solutions. We propose a novel deep CCA model Soft CCA to overcome these problems. Specifically, exact decorrelation is replaced by soft decorrelation via a mini-batch based Stochastic Decorrelation Loss (SDL) to be optimised jointly with the other training objectives. Extensive experiments show that the proposed soft CCA is more effective and efficient than existing deep CCA models. In addition, our SDL loss can be applied to other deep models beyond multi-view learning, and obtains superior performance compared to existing decorrelation losses.

This paper addresses the task of dense non-rigid structure-from-motion (NRSfM) using multiple images. State-of-the-art methods to this problem are often hurdled by scalability, expensive computations, and noisy measurements. Further, recent methods to NRSfM usually either assume a small number of sparse feature points or ignore local non-linearities of shape deformations, and thus cannot reliably model complex non-rigid deformations. To address these issues, in this paper, we propose a new approach for dense NRSfM by modeling the problem on a Grassmann manifold. Specifically, we assume the complex non-rigid deformations lie on a union of local linear subspaces both spatially and temporally. This naturally allows for a compact representation of the complex non-rigid deformation over frames. We provide experimental results on several synthetic and real benchmark datasets. The procured results clearly demonstrate that our method, apart from being scalable and more accurate than state-of-the-art methods, is also more robust to noise and generalizes to highly non-linear deformations.

Research in visual saliency has been focused on two major types of models namely fixation prediction and salient object detection. The relationship between the two, however, has been less explored. In this paper, we propose to employ the former model type to identify and segment salient objects in scenes. We build a novel neural network called Attentive Saliency Network (ASNet) that learns to detect salient objects from fixation maps. The fixation map, derived at the upper network layers, captures a high-level understanding of the scene. Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner. ASNet is based on a hierarchy of convolutional LSTMs (convLSTMs) that offers an efficient recurrent mechanism for sequential refinement of the segmentation map. Several loss functions are introduced for boosting the performance of the ASNet. Extensive experimental evaluation shows that our proposed ASNet is capable of generating accurate segmentation maps with the help of the computed fixation map. Our work offers a deeper insight into the mechanisms of attention and narrows the gap between salient object detection and fixation prediction.

Multi-layer light field displays are a type of computational three-dimensional (3D) display which has recently gained increasing interest for its holographic-like effect and natural compatibility with 2D displays. However, the major shortcoming, depth limitation, still cannot be overcome in the traditional light field modeling and reconstruction based on multi-layer liquid crystal displays (LCDs). Considering this disadvantage, our paper incorporates a salience guided depth optimization over a limited display range to calibrate the displayed depth and present the maximum area of salience region for multi-layer light field display. Different from previously reported cascaded light field displays that use the fixed initialization plane as the depth center of display content, our method automatically calibrates the depth initialization based on the salience results derived from the proposed contrast enhanced salience detection method. Experiments demonstrate that the proposed method provides a promising advantage in visual perception for the compressive light field displays from both software simulation and prototype demonstration.

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or activations during training by approximating their distributions with a limited entry codebook. For very low-precisions, such as binary or ternary networks with 1-8-bit activations, the information loss from quantization leads to significant accuracy degradation due to large gradient mismatches between the forward and backward functions. In this paper, we introduce a quantization method to reduce this loss by learning a symmetric codebook for particular weight subgroups. These subgroups are determined based on their locality in the weight matrix, such that the hardware simplicity of the low-precision representations is preserved. Empirically, we show that symmetric quantization can substantially improve accuracy for networks with extremely low-precision weights and activations. We also demonstrate that this representation imposes minimal or no hardware implications to more coarse-grained approaches. Source code is available at https://www.github.com/julianfaraone/SYQ.

We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN) architecture that utilizes Spatial Transformer Networks (STNs) as the generator, which we call Spatial Transformer GANs (ST-GANs). ST-GANs seek image realism by operating in the geometric warp parameter space. In particular, we exploit an iterative STN warping scheme and propose a sequential training strategy that achieves better results compared to naive training of a single generator. One of the key advantages of ST-GAN is its applicability to high-resolution images indirectly since the predicted warp parameters are transferable between reference frames. We demonstrate our approach in two applications: (1) visualizing how indoor furniture (e.g. from product images) might be perceived in a room, (2) hallucinating how accessories like glasses would look when matched with real portraits.

In action prediction (early action recognition), the goal is to predict the class label of an ongoing action using its observed part so far. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the time axis. As there are significant temporal scale variations of the observed part of the ongoing action at different progress levels, we propose a novel window scale selection scheme to make our network focus on the performed part of the ongoing action and try to suppress the noise from the previous actions at each time step. Furthermore, an activation sharing scheme is proposed to deal with the overlapping computations among the adjacent steps, which allows our model to run more efficiently. The extensive experiments on two challenging datasets show the effectiveness of the proposed action prediction framework.

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, our network uses sparse bilateral convolutional layers as building blocks. These layers maintain efficiency by using indexing structures to apply convolutions only on occupied parts of the lattice, and allow flexible specifications of the lattice structure enabling hierarchical and spatially-aware feature learning, as well as joint 2D-3D reasoning. Both point-based and image-based representations can be easily incorporated in a network with such layers and the resulting model can be trained in an end-to-end manner. We present results on 3D segmentation tasks where our approach outperforms existing state-of-the-art techniques.

This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net performs hierarchical feature extraction on individual points and SOM nodes, and ultimately represents the input point cloud by a single feature vector. The receptive field of the network can be systematically adjusted by conducting point-to-node k nearest neighbor search. In recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval, our proposed network demonstrates performance that is similar with or better than state-of-the-art approaches. In addition, the training speed is significantly faster than existing point cloud recognition networks because of the parallelizability and simplicity of the proposed architecture. Our code is available at the project website.

Existing visual trackers are easily disturbed by occlusion,blurandlargedeformation. Inthechallengesofocclusion, motion blur and large object deformation, the performance of existing visual trackers may be limited due to the followingissues: i)Adoptingthedensesamplingstrategyto generate positive examples will make them less diverse; ii) Thetrainingdatawithdifferentchallengingfactorsarelimited, even though through collecting large training dataset. Collecting even larger training dataset is the most intuitive paradigm, but it may still can not cover all situations and the positive samples are still monotonous. In this paper, we propose to generate hard positive samples via adversarial learning for visual tracking. Specifically speaking, we assume the target objects all lie on a manifold, hence, we introduce the positive samples generation network (PSGN) to sampling massive diverse training data through traversing over the constructed target object manifold. The generated diverse target object images can enrich the training dataset and enhance the robustness of visual trackers. To make the tracker more robust to occlusion, we adopt the hard positive transformation network (HPTN) which can generate hard samples for tracking algorithm to recognize. We train this network with deep reinforcement learning to automaticallyoccludethetargetobjectwithanegativepatch. Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm.

We introduce Similarity Group Proposal Network (SGPN), a simple and intuitive deep learning framework for 3D object instance segmentation on point clouds. SGPN uses a single network to predict point grouping proposals and a corresponding semantic class for each proposal, from which we can directly extract instance segmentation results. Important to the effectiveness of SGPN is its novel representation of 3D instance segmentation results in the form of a similarity matrix that indicates the similarity between each pair of points in embedded feature space, thus producing an accurate grouping proposal for each point. To the best of our knowledge, SGPN is the first framework to learn 3D instance-aware semantic segmentation on point clouds. Experimental results on various 3D scenes show the effectiveness of our method on 3D instance segmentation, and we also evaluate the capability of SGPN to improve 3D object detection and semantic segmentation results. We also demonstrate its flexibility by seamlessly incorporating 2D CNN features into the framework to boost performance.