ICCV 2019 论文列表

As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape. This formulation allows us to both sample shapes and sample an arbitrary number of points from a shape. Our generative model, named PointFlow, learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. The code is available at https://github.com/stevenygd/PointFlow.

3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise importance w.r.t. classification performance, which is usually reflected by a saliency map. A saliency map is an important tool as it allows one to perform further processes on point-cloud data. In this paper, we propose a novel way of characterizing critical points and segments to build point-cloud saliency maps. Our method assigns each point a score reflecting its contribution to the model-recognition loss. The saliency map explicitly explains which points are the key for model recognition. Furthermore, aggregations of highly-scored points indicate important segments/subsets in a point-cloud. Our motivation for constructing a saliency map is by point dropping, which is a non-differentiable operator. To overcome this issue, we approximate point-dropping with a differentiable procedure of shifting points towards the cloud centroid. Consequently, each saliency score can be efficiently measured by the corresponding gradient of the loss w.r.t the point under the spherical coordinates. Extensive evaluations on several state-of-the-art point-cloud recognition models, including PointNet, PointNet++ and DGCNN, demonstrate the veracity and generality of our proposed saliency map. Code for experiments is released on https://github.com/tianzheng4/PointCloud-Saliency-Maps

We introduce Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS). Distinct from existing cost volume approaches, our method directly processes the target scene as point clouds. More specifically, our method predicts the depth in a coarse-to-fine manner. We first generate a coarse depth map, convert it into a point cloud and refine the point cloud iteratively by estimating the residual between the depth of the current iteration and that of the ground truth. Our network leverages 3D geometry priors and 2D texture information jointly and effectively by fusing them into a feature-augmented point cloud, and processes the point cloud to estimate the 3D flow for each point. This point-based architecture allows higher accuracy, more computational efficiency and more flexibility than cost-volume-based counterparts. Experimental results show that our approach achieves a significant improvement in reconstruction quality compared with state-of-the-art methods on the DTU and the Tanks and Temples dataset. Our source code and trained models are available at https://github.com/callmeray/PointMVSNet.

Estimating the 6D pose of objects using only RGB images remains challenging because of problems such as occlusion and symmetries. It is also difficult to construct 3D models with precise texture without expert knowledge or specialized scanning devices. To address these problems, we propose a novel pose estimation method, Pix2Pose, that predicts the 3D coordinates of each object pixel without textured models. An auto-encoder architecture is designed to estimate the 3D coordinates and expected errors per pixel. These pixel-wise predictions are then used in multiple stages to form 2D-3D correspondences to directly compute poses with the PnP algorithm with RANSAC iterations. Our method is robust to occlusion by leveraging recent achievements in generative adversarial training to precisely recover occluded parts. Furthermore, a novel loss function, the transformer loss, is proposed to handle symmetric objects by guiding predictions to the closest symmetric pose. Evaluations on three different benchmark datasets containing symmetric and occluded objects show our method outperforms the state of the art using only RGB images.

Localizing phrases in images is an important part of image understanding and can be useful in many applications that require mappings between textual and visual information. Existing work attempts to learn these mappings from examples of phrase-image region correspondences (strong supervision) or from phrase-image pairs (weak supervision). We postulate that such paired annotations are unnecessary, and propose the first method for the phrase localization problem where neither training procedure nor paired, task-specific data is required. Our method is simple but effective: we use off-the-shelf approaches to detect objects, scenes and colours in images, and explore different approaches to measure semantic similarity between the categories of detected visual elements and words in phrases. Experiments on two well-known phrase localization datasets show that this approach surpasses all weakly supervised methods by a large margin and performs very competitively to strongly supervised methods, and can thus be considered a strong baseline to the task. The non-paired nature of our method makes it applicable to any domain and where no paired phrase localization annotation is available.

We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervised and unsupervised learning for facial detail synthesis. On proxy generation, we conduct emotion prediction to determine a new expression-informed proxy. On detail synthesis, we present a Deep Facial Detail Net (DFDN) based on Conditional Generative Adversarial Net (CGAN) that employs both geometry and appearance loss functions. For geometry, we capture 366 high-quality 3D scans from 122 different subjects under 3 facial expressions. For appearance, we use additional 163K in-the-wild face images and apply image-based rendering to accommodate lighting variations. Comprehensive experiments demonstrate that our framework can produce high-quality 3D faces with realistic details under challenging facial expressions.

In this paper, we analyze the inner product of weight vector w and data vector x in neural networks from the perspective of vector orthogonal decomposition and prove that the direction gradient of w decreases with the angle between them close to 0 or p. We propose the Projection and Rejection Product (PR Product) to make the direction gradient of w independent of the angle and consistently larger than the one in standard inner product while keeping the forward propagation identical. As a reliable substitute for standard inner product, the PR Product can be applied into many existing deep learning modules, so we develop the PR Product version of fully connected layer, convolutional layer and LSTM layer. In static image classification, the experiments on CIFAR10 and CIFAR100 datasets demonstrate that the PR Product can robustly enhance the ability of various state-of-the-art classification networks. On the task of image captioning, even without any bells and whistles, our PR Product version of captioning model can compete or outperform the state-of-the-art models on MS COCO dataset. Code has been made available at: https://github.com/wzn0828/PR_Product.

We present a complete classification of all minimal problems for generic arrangements of points and lines completely observed by calibrated perspective cameras. We show that there are only 30 minimal problems in total, no problems exist for more than 6 cameras, for more than 5 points, and for more than 6 lines. We present a sequence of tests for detecting minimality starting with counting degrees of freedom and ending with full symbolic and numeric verification of representative examples. For all minimal problems discovered, we present their algebraic degrees, i.e. the number of solutions, which measure their intrinsic difficulty. It shows how exactly the difficulty of problems grows with the number of views. Importantly, several new mini- mal problems have small degrees that might be practical in image matching and 3D reconstruction.

Pedestrian behavior anticipation is a key challenge in the design of assistive and autonomous driving systems suitable for urban environments. An intelligent system should be able to understand the intentions or underlying motives of pedestrians and to predict their forthcoming actions. To date, only a few public datasets were proposed for the purpose of studying pedestrian behavior prediction in the context of intelligent driving. To this end, we propose a novel large-scale dataset designed for pedestrian intention estimation (PIE). We conducted a large-scale human experiment to establish human reference data for pedestrian intention in traffic scenes. We propose models for estimating pedestrian crossing intention and predicting their future trajectory. Our intention estimation model achieves 79% accuracy and our trajectory prediction algorithm outperforms state-of-the-art by 26% on the proposed dataset. We further show that combining pedestrian intention with observed motion improves trajectory prediction. The dataset and models are available at http://data.nvision2.eecs.yorku.ca/PIE_dataset/.

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus been developed to learn to perform segmentation from only a few annotated examples. In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set. Our PANet learns class-specific prototype representations from a few support images within an embedding space and then performs segmentation over the query images through matching each pixel to the learned prototypes. With non-parametric metric learning, PANet offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. Moreover, PANet introduces a prototype alignment regularization between support and query. With this, PANet fully exploits knowledge from the support and provides better generalization on few-shot segmentation. Significantly, our model achieves the mIoU score of 48.1% and 55.7% on PASCAL-5i for 1-shot and 5-shot settings respectively, surpassing the state-of-the-art method by 1.8% and 8.6%.

Weakly supervised object detection (WSOD), where a detector is trained with only image-level annotations, is attracting more and more attention. As a method to obtain a well-performing detector, the detector and the instance labels are updated iteratively. In this study, for more efficient iterative updating, we focus on the instance labeling problem, a problem of which label should be annotated to each region based on the last localization result. Instead of simply labeling the top-scoring region and its highly overlapping regions as positive and others as negative, we propose more effective instance labeling methods as follows. First, to solve the problem that regions covering only some parts of the object tend to be labeled as positive, we find regions covering the whole object focusing on the context classification loss. Second, considering the situation where the other objects contained in the image can be labeled as negative, we impose a spatial restriction on regions labeled as negative. Using these instance labeling methods, we train the detector on the PASCAL VOC 2007 and 2012 and obtain significantly improved results compared with other state-of-the-art approaches.

Not all the human body parts have the same degree of freedom (DOF) due to the physiological structure. For example, the limbs may move more flexibly and freely than the torso does. Most of the existing 3D pose estimation methods, despite the very promising results achieved, treat the body joints equally and consequently often lead to larger reconstruction errors on the limbs. In this paper, we propose a progressive approach that explicitly accounts for the distinct DOFs among the body parts. We model parts with higher DOFs like the elbows, as dependent components of the corresponding parts with lower DOFs like the torso, of which the 3D locations can be more reliably estimated. Meanwhile, the high-DOF parts may, in turn, impose a constraint on where the low-DOF ones lie. As a result, parts with different DOFs supervise one another, yielding physically constrained and plausible pose-estimation results. To further facilitate the prediction of the high-DOF parts, we introduce a pose-attribution estimation, where the relative location of a limb joint with respect to the torso, which has the least DOF of a human body, is explicitly estimated and further fed to the joint-estimation module. The proposed approach achieves very promising results, outperforming the state of the art on several benchmarks.

Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since one-order interactions cannot be maintained for a long term due to information dilution and gradient vanishing. To tackle this limitation, we propose the Non-local Recurrent Neural Memory (NRNM) for supervised sequence modeling, which performs non-local operations to learn full-order interactions within a sliding temporal block and models the global interactions between blocks in a gated recurrent manner. Consequently, our model is able to capture the long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We demonstrate the merits of our NRNM approach on two different tasks: action recognition and sentiment analysis.

Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a coarse approximation of real sensor noise. This paper introduces Noise Flow, a powerful and accurate noise model based on recent normalizing flow architectures. Noise Flow combines well-established basic parametric noise models (e.g., signal-dependent noise) with the flexibility and expressiveness of normalizing flow networks. The result is a single, comprehensive, compact noise model containing fewer than 2500 parameters yet able to represent multiple cameras and gain factors. Noise Flow dramatically outperforms existing noise models, with 0.42 nats/pixel improvement over the camera-calibrated noise level functions, which translates to 52% improvement in the likelihood of sampled noise. Noise Flow represents the first serious attempt to go beyond simple parametric models to one that leverages the power of deep learning and data-driven noise distributions.

We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts. Specifically, we represent the road layout using a graph where nodes in the graph represent control points and edges in the graph represents road segments. NTG is a sequential generative model parameterized by a neural network. It iteratively generates a new node and an edge connecting to an existing node conditioned on the current graph. We train NTG on Open Street Map data and show it outperforms existing approaches using a set of diverse performance metrics. Moreover, our method allows users to control styles of generated road layouts mimicking existing cities as well as to sketch a part of the city road layout to be synthesized. In addition to synthesis, the proposed NTG finds uses in an analytical task of aerial road parsing. Experimental results show that it achieves state-of-the-art performance on the SpaceNet dataset.

Architectures obtained by Neural Architecture Search (NAS) have achieved highly competitive performance in various computer vision tasks. However, the prohibitive computation demand of forward-backward propagation in deep neural networks and searching algorithms makes it difficult to apply NAS in practice. In this paper, we propose a Multinomial Distribution Learning for extremely effective NAS, which considers the search space as a joint multinomial distribution, i.e., the operation between two nodes is sampled from this distribution, and the optimal network structure is obtained by the operations with the most likely probability in this distribution. Therefore, NAS can be transformed to a multinomial distribution learning problem, i.e., the distribution is optimized to have a high expectation of the performance. Besides, a hypothesis that the performance ranking is consistent in every training epoch is proposed and demonstrated to further accelerate the learning process. Experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of our method. On CIFAR-10, the structure searched by our method achieves 2.55% test error, while being 6.0x (only 4 GPU hours on GTX1080Ti) faster compared with state-of-the-art NAS algorithms. On ImageNet, our model achieves 74% top1 accuracy under MobileNet settings (MobileNet V1/V2), while being 1.2x faster with measured GPU latency. Test code with pre-trained models are available at https: //github.com/tanglang96/MDENAS

Object part parsing in the wild, which requires to simultaneously detect multiple object classes in the scene and accurately segments semantic parts within each class, is challenging for the joint presence of class-level and part-level ambiguities. Despite its importance, however, this problem is not sufficiently explored in existing works. In this paper, we propose a joint parsing framework with boundary and semantic awareness to address this challenging problem. To handle part-level ambiguity, a boundary awareness module is proposed to make mid-level features at multiple scales attend to part boundaries for accurate part localization, which are then fused with high-level features for effective part recognition. For class-level ambiguity, we further present a semantic awareness module that selects discriminative part features relevant to a category to prevent irrelevant features being merged together. The proposed modules are lightweight and implementation friendly, improving the performance substantially when plugged into various baseline architectures. Without bells and whistles, the full model sets new state-of-the-art results on the Pascal-Part dataset, in both multi-class and the conventional single-class setting, while running substantially faster than recent high-performance approaches.

Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted frame sampling strategies for recognition. It could degrade the performance, especially in untrimmed videos, due to the variation of frame-level saliency. To this end, we concentrate on improving untrimmed video classification via developing a learning-based frame sampling strategy. We intuitively formulate the frame sampling procedure as multiple parallel Markov decision processes, each of which aims at picking out a frame/clip by gradually adjusting an initial sampling. Then we propose to solve the problems with multi-agent reinforcement learning (MARL). Our MARL framework is composed of a novel RNN-based context-aware observation network which jointly models context information among nearby agents and historical states of a specific agent, a policy network which generates the probability distribution over a predefined action space at each step and a classification network for reward calculation as well as final recognition. Extensive experimental results show that our MARL-based scheme remarkably outperforms hand-crafted strategies with various 2D and 3D baseline methods. Our single RGB model achieves a comparable performance of ActivityNet v1.3 champion submission with multi-modal multi-model fusion and new state-of-the-art results on YouTube Birds and YouTube Cars.

Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning approach, Moment Matching for Multi-Source Domain Adaptation (M3SDA), which aims to transfer knowledge learned from multiple labeled source domains to an unlabeled target domain by dynamically aligning moments of their feature distributions. Third, we provide new theoretical insights specifically for moment matching approaches in both single and multiple source domain adaptation. Extensive experiments are conducted to demonstrate the power of our new dataset in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model. Dataset and Code are available at http://ai.bu.edu/M3SDA/