CVPR 2020 论文列表

We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the motion parameters that align the scans into a common reference frame. With regard to regression, we present two alternative approaches: (i) a Deep Neural Network (DNN) registration and (ii) a Procrustes approach using SVD to estimate the transformation. Our correspondence-based approach achieves a higher speedup compared to competing baselines. We further propose the use of a refinement network, which consists of a smaller 3DRegNet as a refinement to improve the accuracy of the registration. Extensive experiments on two challenging datasets demonstrate that we outperform other methods and achieve state-of-the-art results. The code is available.

In this work we present a novel publicly available stereo based 3D RGB dataset for multi-object zebrafish tracking, called 3D-ZeF. Zebrafish is an increasingly popular model organism used for studying neurological disorders, drug addiction, and more. Behavioral analysis is often a critical part of such research. However, visual similarity, occlusion, and erratic movement of the zebrafish makes robust 3D tracking a challenging and unsolved problem. The proposed dataset consists of eight sequences with a duration between 15-120 seconds and 1-10 free moving zebrafish. The videos have been annotated with a total of 86,400 points and bounding boxes. Furthermore, we present a complexity score and a novel open-source modular baseline system for 3D tracking of zebrafish. The performance of the system is measured with respect to two detectors: a naive approach and a Faster R-CNN based fish head detector. The system reaches a MOTA of up to 77.6%. Links to the code and dataset is available at the project page http://vap.aau.dk/3d-zef

We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-proposal relations, providing higher-level feature learning in addition to the lower-level point features. Each proposal comprises a semantic label, a set of associated points over which we define a foreground-background mask, an objectness score and aggregation features. Previous works usually perform non-maximum-suppression (NMS) over proposals to obtain the final object detections or semantic instances. However, NMS can discard potentially correct predictions. Instead, our approach keeps all proposals and groups them together based on the learned aggregation features. We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.

The goal of the Semantic Scene Completion (SSC) task is to simultaneously predict a completed 3D voxel representation of volumetric occupancy and semantic labels of objects in the scene from a single-view observation. Since the computational cost generally increases explosively along with the growth of voxel resolution, most current state-of-the-arts have to tailor their framework into a low-resolution representation with the sacrifice of detail prediction. Thus, voxel resolution becomes one of the crucial difficulties that lead to the performance bottleneck. In this paper, we propose to devise a new geometry-based strategy to embed depth information with low-resolution voxel representation, which could still be able to encode sufficient geometric information, e.g., room layout, object's sizes and shapes, to infer the invisible areas of the scene with well structure-preserving details. To this end, we first propose a novel 3D sketch-aware feature embedding to explicitly encode geometric information effectively and efficiently. With the 3D sketch in hand, we further devise a simple yet effective semantic scene completion framework that incorporates a light-weight 3D Sketch Hallucination module to guide the inference of occupancy and the semantic labels via a semi-supervised structure prior learning strategy. We demonstrate that our proposed geometric embedding works better than the depth feature learning from habitual SSC frameworks. Our final model surpasses state- of-the-arts consistently on three public benchmarks, which only requires 3D volumes of 60 x 36 x 60 resolution for both input and output.

We propose a method for converting a single RGB-D input image into a 3D photo, i.e., a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view. We use a Layered Depth Image with explicit pixel connectivity as underlying representation, and present a learning-based inpainting model that iteratively synthesizes new local color-and-depth content into the occluded region in a spatial context-aware manner. The resulting 3D photos can be efficiently rendered with motion parallax using standard graphics engines. We validate the effectiveness of our method on a wide range of challenging everyday scenes and show less artifacts when compared with the state-of-the-arts.

Holistically understanding an object with its 3D movable parts is essential for visual models of a robot to interact with the world. For example, only by understanding many possible part dynamics of other vehicles (e.g., door or trunk opening, taillight blinking for changing lane), a self-driving vehicle can be success in dealing with emergency cases. However, existing visual models tackle rarely on these situations, but focus on bounding box detection. In this paper, we fill this important missing piece in autonomous driving by solving two critical issues. First, for dealing with data scarcity, we propose an effective training data generation process by fitting a 3D car model with dynamic parts to cars in real images. This allows us to directly edit the real images using the aligned 3D parts, yielding effective training data for learning robust deep neural networks (DNNs). Secondly, to benchmark the quality of 3D part understanding, we collected a large dataset in real driving scenario with cars in uncommon states (CUS), i.e. with door or trunk opened etc., which demonstrates that our trained network with edited images largely outperforms other baselines in terms of 2D detection and instance segmentation accuracy.

Estimating 3D mesh of the human body from a single 2D image is an important task with many applications such as augmented reality and Human-Robot interaction. However, prior works reconstructed 3D mesh from global image feature extracted by using convolutional neural network (CNN), where the dense correspondences between the mesh surface and the image pixels are missing, leading to suboptimal solution. This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i.e. a 2D space used for texture mapping of 3D mesh). DecoMR first predicts pixel-to-surface dense correspondence map (i.e., IUV image), with which we transfer local features from the image space to the UV space. Then the transferred local image features are processed in the UV space to regress a location map, which is well aligned with transferred features. Finally we reconstruct 3D human mesh from the regressed location map with a predefined mapping function. We also observe that the existing discontinuous UV map are unfriendly to the learning of network. Therefore, we propose a novel UV map that maintains most of the neighboring relations on the original mesh surface. Experiments demonstrate that our proposed local feature alignment and continuous UV map outperforms existing 3D mesh based methods on multiple public benchmarks. Code will be made available at https: //github.com/zengwang430521/DecoMR.

Pose-tracking is an important problem that requires identifying unique human pose-instances and matching them temporally across different frames in a video. However, existing pose-tracking methods are unable to accurately model temporal relationships and require significant computation, often computing the tracks offline. We present an efficient multi-person pose-tracking method, KeyTrack that only relies on keypoint information without using any RGB or optical flow to locate and track human keypoints in real-time. KeyTrack is a top-down approach that learns spatio-temporal pose relationships by modeling the multi-person pose-tracking problem as a novel Pose Entailment task using a Transformer based architecture. Furthermore, KeyTrack uses a novel, parameter-free, keypoint refinement technique that improves the keypoint estimates used by the Transformers. We achieve state-of-the-art results on PoseTrack'17 and PoseTrack'18 benchmarks while using only a fraction of the computation used by most other methods for computing the tracking information.

Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these tasks overlap significantly. In this work, we investigate these relationships between vision-and-language tasks by developing a large-scale, multi-task model. Our approach culminates in a single model on 12 datasets from four broad categories of task including visual question answering, caption-based image retrieval, grounding referring expressions, and multimodal verification. Compared to independently trained single-task models, this represents a reduction from approximately 3 billion parameters to 270 million while simultaneously improving performance by 2.05 points on average across tasks. We use our multi-task framework to perform in-depth analysis of the effect of joint training diverse tasks. Further, we show that finetuning task-specific models from our single multi-task model can lead to further improvements, achieving performance at or above the state-of-the-art.

In recent years, predicting driver's focus of attention has been a very active area of research in the autonomous driving community. Unfortunately, existing state-of-the-art techniques achieve this by relying only on human gaze information, thereby ignoring scene semantics. We propose a novel Semantics Augmented GazE (SAGE) detection approach that captures driving specific contextual information, in addition to the raw gaze. Such a combined attention mechanism serves as a powerful tool to focus on the relevant regions in an image frame in order to make driving both safe and efficient. Using this, we design a complete saliency prediction framework - SAGE-Net, which modifies the initial prediction from SAGE by taking into account vital aspects such as distance to objects (depth), ego vehicle speed, and pedestrian crossing intent. Exhaustive experiments conducted through four popular saliency algorithms show that on 49/56 (87.5%) cases - considering both the overall dataset and crucial driving scenarios, SAGE outperforms existing techniques without any additional computational overhead during the training process. The augmented dataset along with the relevant code are available as part of the supplementary material.