CVPR 2019 Papers

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots. The new method, PifPaf, uses a Part Intensity Field (PIF) to localize body parts and a Part Association Field (PAF) to associate body parts with each other to form full human poses. Our method outperforms previous methods at low resolution and in crowded, cluttered and occluded scenes thanks to (i) our new composite field PAF encoding fine-grained information and (ii) the choice of Laplace loss for regressions which incorporates a notion of uncertainty. Our architecture is based on a fully convolutional, single-shot, box-free design. We perform on par with the existing state-of-the-art bottom-up method on the standard COCO keypoint task and produce state-of-the-art results on a modified COCO keypoint task for the transportation domain.

Single-photon avalanche diodes (SPADs) are starting to play a pivotal role in the development of photon-efficient, long-range LiDAR systems. However, due to non-linearities in their image formation model, a high photon flux (e.g., due to strong sunlight) leads to distortion of the incident temporal waveform, and potentially, large depth errors. Operating SPADs in low flux regimes can mitigate these distortions, but, often requires attenuating the signal and thus, results in low signal-to-noise ratio. In this paper, we address the following basic question: what is the optimal photon flux that a SPAD-based LiDAR should be operated in? We derive a closed form expression for the optimal flux, which is quasi-depth-invariant, and depends on the ambient light strength. The optimal flux is lower than what a SPAD typically measures in real world scenarios, but surprisingly, considerably higher than what is conventionally suggested for avoiding distortions. We propose a simple, adaptive approach for achieving the optimal flux by attenuating incident flux based on an estimate of ambient light strength. Using extensive simulations and a hardware prototype, we show that the optimal flux criterion holds for several depth estimators, under a wide range of illumination conditions.

In this paper, we address the problem of 3D object mesh reconstruction from RGB videos. Our approach combines the best of multi-view geometric and data-driven methods for 3D reconstruction by optimizing object meshes for multi-view photometric consistency while constraining mesh deformations with a shape prior. We pose this as a piecewise image alignment problem for each mesh face projection. Our approach allows us to update shape parameters from the photometric error without any depth or mask information. Moreover, we show how to avoid a degeneracy of zero photometric gradients via rasterizing from a virtual viewpoint. We demonstrate 3D object mesh reconstruction results from both synthetic and real-world videos with our photometric mesh optimization, which is unachievable with either naive mesh generation networks or traditional pipelines of surface reconstruction without heavy manual post-processing.

We present a method and application for animating a human subject from a single photo. E.g., the character can walk out, run, sit, or jump in 3D. The key contributions of this paper are: 1) an application of viewing and animating humans in single photos in 3D, 2) a novel 2D warping method to deform a posable template body model to fit the person's complex silhouette to create an animatable mesh, and 3) a method for handling partial self occlusions. We compare to state-of-the-art related methods and evaluate results with human studies. Further, we present an interactive interface that allows re-posing the person in 3D, and an augmented reality setup where the animated 3D person can emerge from the photo into the real world. We demonstrate the method on photos, posters, and art. The project page is at https://grail.cs.washington.edu/projects/wakeup/.

The image motion blurring process is generally modelled as the convolution of a blur kernel with a latent image. Therefore, the estimation of the blur kernel is essentially important for blind image deblurring. Unlike existing approaches which focus on approaching the problem by enforcing various priors on the blur kernel and the latent image, we are aiming at obtaining a high quality blur kernel directly by studying the problem in the frequency domain. We show that the auto-correlation of the absolute phase-only image 1 can provide faithful information about the motion (e.g., the motion direction and magnitude, we call it the motion pattern in this paper.) that caused the blur, leading to a new and efficient blur kernel estimation approach. The blur kernel is then refined and the sharp image is estimated by solving an optimization problem by enforcing a regularization on the blur kernel and the latent image. We further extend our approach to handle non-uniform blur, which involves spatially varying blur kernels. Our approach is evaluated extensively on synthetic and real data and shows good results compared to the state-of-the-art deblurring approaches.

This paper presents a perturbation analysis for the estimate of epipolar matrices using the 8-Point Algorithm (8-PA). Our approach explores existing bounds for singular subspaces and relates them to the 8-PA, without assuming any kind of error distribution for the matched features. In particular, if we use unit vectors as homogeneous image coordinates, we show that having a wide spatial distribution of matched features in both views tends to generate lower error bounds for the epipolar matrix error. Our experimental validation indicates that the bounds and the effective errors tend to decrease as the camera Field of View (FoV) increases, and that using the 8-PA for spherical images (that present 360degx180deg FoV) leads to accurate essential matrices. As an additional contribution, we present bounds for the direction of the translation vector extracted from the essential matrix based on singular subspace analysis.

This paper considers a realistic problem in person re-identification (re-ID) task, i.e., partial re-ID. Under partial re-ID scenario, the images may contain a partial observation of a pedestrian. If we directly compare a partial pedestrian image with a holistic one, the extreme spatial misalignment significantly compromises the discriminative ability of the learned representation. We propose a Visibility-aware Part Model (VPM) for partial re-ID, which learns to perceive the visibility of regions through self-supervision. The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images). VPM gains two-fold benefit toward higher accuracy for partial re-ID. On the one hand, compared with learning a global feature, VPM learns region-level features and thus benefits from fine-grained information. On the other hand, with visibility awareness, VPM is capable to estimate the shared regions between two images and thus suppresses the spatial misalignment. Experimental results confirm that our method significantly improves the learned feature representation and the achieved accuracy is on par with the state of the art.

Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in many applications. Motivated by this idea, this paper studies predicting a pedestrian's future path jointly with future activities. We propose an end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings. To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen. Experimental results demonstrate our state-of-the-art performance over two public benchmarks on future trajectory prediction. Moreover, our method is able to produce meaningful future activity prediction in addition to the path. The result provides the first empirical evidence that joint modeling of paths and activities benefits future path prediction.

We present an autoregressive pedestrian detection framework with cascaded phases designed to progressively improve precision. The proposed framework utilizes a novel lightweight stackable decoder-encoder module which uses convolutional re-sampling layers to improve features while maintaining efficient memory and runtime cost. Unlike previous cascaded detection systems, our proposed framework is designed within a region proposal network and thus retains greater context of nearby detections compared to independently processed RoI systems. We explicitly encourage increasing levels of precision by assigning strict labeling policies to each consecutive phase such that early phases develop features primarily focused on achieving high recall and later on accurate precision. In consequence, the final feature maps form more peaky radial gradients emulating from the centroids of unique pedestrians. Using our proposed autoregressive framework leads to new state-of-the-art performance on the reasonable and occlusion settings of the Caltech pedestrian dataset, and achieves competitive state-of-the-art performance on the KITTI dataset.

Several recent studies have demonstrated the promise of deep visuomotor policies for robot manipulator control. Despite impressive progress, these systems are known to be vulnerable to physical disturbances, such as accidental or adversarial bumps that make them drop the manipulated object. They also tend to be distracted by visual disturbances such as objects moving in the robot's field of view, even if the disturbance does not physically prevent the execution of the task. In this paper, we propose an approach for augmenting a deep visuomotor policy trained through demonstrations with Task Focused visual Attention (TFA). The manipulation task is specified with a natural language text such as "move the red bowl to the left". This allows the visual attention component to concentrate on the current object that the robot needs to manipulate. We show that even in benign environments, the TFA allows the policy to consistently outperform a variant with no attention mechanism. More importantly, the new policy is significantly more robust: it regularly recovers from severe physical disturbances (such as bumps causing it to drop the object) from which the baseline policy, i.e. with no visual attention, almost never recovers. In addition, we show that the proposed policy performs correctly in the presence of a wide class of visual disturbances, exhibiting a behavior reminiscent of human selective visual attention experiments.

In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widely-spread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.

Optimizing a network of maps among a collection of objects/domains (or map synchronization) is a central problem across computer vision and many other relevant fields. Compared to optimizing pairwise maps in isolation, the benefit of map synchronization is that there are natural constraints among a map network that can improve the quality of individual maps. While such self-supervision constraints are well-understood for undirected map networks (e.g., the cycle-consistency constraint), they are under-explored for directed map networks, which naturally arise when maps are given by parametric maps (e.g., a feed-forward neural network). In this paper, we study a natural self-supervision constraint for directed map networks called path-invariance, which enforces that composite maps along different paths between a fixed pair of source and target domains are identical. We introduce path-invariance bases for efficient encoding of the path-invariance constraint and present an algorithm that outputs a path-variance basis with polynomial time and space complexities. We demonstrate the effectiveness of our formulation on optimizing object correspondences, estimating dense image maps via neural networks, and 3D scene segmentation via map networks of diverse 3D representations. In particular, our approach only requires 8% labeled data from ScanNet to achieve the same performance as training a single 3D semantic segmentation network with 30% to 100% labeled data.

We present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-the-art learning-based and optimazation-based approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details.

While discriminative local features have been shown effective in solving the person re-identification problem, they are limited to be trained on fully pairwise labelled data which is expensive to obtain. In this work, we overcome this problem by proposing a patch-based unsupervised learning framework in order to learn discriminative feature from patches instead of the whole images. The patch-based learning leverages similarity between patches to learn a discriminative model. Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches. To provide effective guidance for the PatchNet to learn discriminative patch feature on unlabeled datasets, we propose an unsupervised patch-based discriminative feature learning loss. In addition, we design an image-level feature learning loss to leverage all the patch features of the same image to serve as an image-level guidance for the PatchNet. Extensive experiments validate the superiority of our method for unsupervised person re-id. Our code is available at https://github.com/QizeYang/PAUL.

Achieving good speed and accuracy trade-off on a target platform is very important in deploying deep neural networks in real world scenarios. However, most existing automatic architecture search approaches only concentrate on high performance. In this work, we propose an algorithm that can offer better speed/accuracy trade-off of searched networks, which is termed "Partial Order Pruning". It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off. Our algorithm explicitly takes profile information about the inference speed on the target platform into consideration. With the proposed algorithm, we present several Dongfeng (DF) networks that provide high accuracy and fast inference speed on various application GPU platforms. By further searching decoder architectures, our DF-Seg real-time segmentation networks yield state-of-the-art speed/accuracy trade-off on both the target embedded device and the high-end GPU.

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. These models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an arbitrary number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a baseline method for part instance segmentation and demonstrate its superior performance over existing methods.

Vehicle re-identification (Re-ID) has been attracting more interests in computer vision owing to its great contributions in urban surveillance and intelligent transportation. With the development of deep learning approaches, vehicle Re-ID still faces a near-duplicate challenge, which is to distinguish different instances with nearly identical appearances. Previous methods simply rely on the global visual features to handle this problem. In this paper, we proposed a simple but efficient part-regularized discriminative feature preserving method which enhances the perceptive ability of subtle discrepancies. We further develop a novel framework to integrate part constrains with the global Re-ID modules by introducing an detection branch. Our framework is trained end-to-end with combined local and global constrains. Specially, without the part-regularized local constrains in inference step, our Re-ID network outperforms the state-of-the-art method by a large margin on large benchmark datasets VehicleID and VeRi-776.

Instance-level human analysis is common in real-life scenarios and has multiple manifestations, such as human part segmentation, dense pose estimation, human-object interactions, etc. Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance. In this paper, we present an end-to-end pipeline for solving the instance-level human analysis, named Parsing R-CNN. It processes a set of human instances simultaneously through comprehensive considering the characteristics of region-based approach and the appearance of a human, thus allowing representing the details of instances. Parsing R-CNN is very flexible and efficient, which is applicable to many issues in human instance analysis. Our approach outperforms all state-of-the-art methods on CIHP (Crowd Instance-level Human Parsing), MHP v2.0 (Multi-Human Parsing) and DensePose-COCO datasets. Based on the proposed Parsing R-CNN, we reach the 1st place in the COCO 2018 Challenge DensePose Estimation task. Code and models are publicly available.