Peng Wang

Peng Wang, Yuan Liu, Zhaoxi Chen et al.

This paper presents a novel grid-based NeRF called F2-NeRF (Fast-Free-NeRF) for novel view synthesis, which enables arbitrary input camera trajectories and only costs a few minutes for training. Existing fast grid-based NeRF training frameworks, like Instant-NGP, Plenoxels, DVGO, or TensoRF, are mainly designed for bounded scenes and rely on space warping to handle unbounded scenes. Existing two widely-used space-warping methods are only designed for the forward-facing trajectory or the 360-degree object-centric trajectory but cannot process arbitrary trajectories. In this paper, we delve deep into the mechanism of space warping to handle unbounded scenes. Based on our analysis, we further propose a novel space-warping method called perspective warping, which allows us to handle arbitrary trajectories in the grid-based NeRF framework. Extensive experiments demonstrate that F2-NeRF is able to use the same perspective warping to render high-quality images on two standard datasets and a new free trajectory dataset collected by us. Project page: https://totoro97.github.io/projects/f2-nerf.

Jiepeng Wang, Congyi Zhang, Peng Wang et al.

3D reconstruction techniques have widely been used for digital documentation of archaeological fragments. However, efficient digital capture of fragments remains as a challenge. In this work, we aim to develop a portable, high-throughput, and accurate reconstruction system for efficient digitization of fragments excavated in archaeological sites. To realize high-throughput digitization of large numbers of objects, an effective strategy is to perform scanning and reconstruction in batches. However, effective batch-based scanning and reconstruction face two key challenges: 1) how to correlate partial scans of the same object from multiple batch scans, and 2) how to register and reconstruct complete models from partial scans that exhibit only small overlaps. To tackle these two challenges, we develop a new batch-based matching algorithm that pairs the front and back sides of the fragments, and a new Bilateral Boundary ICP algorithm that can register partial scans sharing very narrow overlapping regions. Extensive validation in labs and testing in excavation sites demonstrate that these designs enable efficient batch-based scanning for fragments. We show that such a batch-based scanning and reconstruction pipeline can have immediate applications on digitizing sherds in archaeological excavations. Our project page: https://jiepengwang.github.io/FIRES/.

Yuling Xi, Hao Chen, Ning Wang et al.

Multi-task visual perception has a wide range of applications in scene understanding such as autonomous driving. In this work, we devise an efficient unified framework to solve multiple common perception tasks, including instance segmentation, semantic segmentation, monocular 3D detection, and depth estimation. Simply sharing the same visual feature representations for these tasks impairs the performance of tasks, while independent task-specific feature extractors lead to parameter redundancy and latency. Thus, we design two feature-merge branches to learn feature basis, which can be useful to, and thus shared by, multiple perception tasks. Then, each task takes the corresponding feature basis as the input of the prediction task head to fulfill a specific task. In particular, one feature merge branch is designed for instance-level recognition the other for dense predictions. To enhance inter-branch communication, the instance branch passes pixel-wise spatial information of each instance to the dense branch using efficient dynamic convolution weighting. Moreover, a simple but effective dynamic routing mechanism is proposed to isolate task-specific features and leverage common properties among tasks. Our proposed framework, termed D2BNet, demonstrates a unique approach to parameter-efficient predictions for multi-task perception. In addition, as tasks benefit from co-training with each other, our solution achieves on par results on partially labeled settings on nuScenes and outperforms previous works for 3D detection and depth estimation on the Cityscapes dataset with full supervision.

Caiyuan Zheng, Hui Li, Seon-Min Rhee et al.

Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes a lot to STR, it suffers from the real-tosynthetic domain gap that restricts model performance. In this work, we aim to boost STR models by leveraging both synthetic data and the numerous real unlabeled images, exempting human annotation cost thoroughly. A robust consistency regularization based semi-supervised framework is proposed for STR, which can effectively solve the instability issue due to domain inconsistency between synthetic and real images. A character-level consistency regularization is designed to mitigate the misalignment between characters in sequence recognition. Extensive experiments on standard text recognition benchmarks demonstrate the effectiveness of the proposed method. It can steadily improve existing STR models, and boost an STR model to achieve new state-of-the-art results. To our best knowledge, this is the first consistency regularization based framework that applies successfully to STR.

Chenxu Luo, Zhenheng Yang, Peng Wang et al.

Learning to estimate 3D geometry in a single frame and optical flow from consecutive frames by watching unlabeled videos via deep convolutional network has made significant progress recently. Current state-of-the-art (SoTA) methods treat the two tasks independently. One typical assumption of the existing depth estimation methods is that the scenes contain no independent moving objects. while object moving could be easily modeled using optical flow. In this paper, we propose to address the two tasks as a whole, i.e. to jointly understand per-pixel 3D geometry and motion. This eliminates the need of static scene assumption and enforces the inherent geometrical consistency during the learning process, yielding significantly improved results for both tasks. We call our method as "Every Pixel Counts++" or "EPC++". Specifically, during training, given two consecutive frames from a video, we adopt three parallel networks to predict the camera motion (MotionNet), dense depth map (DepthNet), and per-pixel optical flow between two frames (OptFlowNet) respectively. The three types of information are fed into a holistic 3D motion parser (HMP), and per-pixel 3D motion of both rigid background and moving objects are disentangled and recovered. Comprehensive experiments were conducted on datasets with different scenes, including driving scenario (KITTI 2012 and KITTI 2015 datasets), mixed outdoor/indoor scenes (Make3D) and synthetic animation (MPI Sintel dataset). Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods. Code will be available at: https://github.com/chenxuluo/EPC.

Yang Wang, Zhenheng Yang, Peng Wang et al.

Learning depth and optical flow via deep neural networks by watching videos has made significant progress recently. In this paper, we jointly solve the two tasks by exploiting the underlying geometric rules within stereo videos. Specifically, given two consecutive stereo image pairs from a video, we first estimate depth, camera ego-motion and optical flow from three neural networks. Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion. We propose a novel consistency loss to let the optical flow learn from the more accurate rigid flow in static regions. We also design a rigid alignment module which helps refine ego-motion estimation by using the estimated depth and optical flow. Experiments on the KITTI dataset show that our results significantly outperform other state-of- the-art algorithms. Source codes can be found at https: //github.com/baidu-research/UnDepthflow

Xinjing Cheng, Peng Wang, Ruigang Yang

Depth prediction is one of the fundamental problems in computer vision. In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for various depth estimation tasks. Specifically, it is an efficient linear propagation model, in which the propagation is performed with a manner of recurrent convolutional operation, and the affinity among neighboring pixels is learned through a deep convolutional neural network (CNN). We can append this module to any output from a state-of-the-art (SOTA) depth estimation networks to improve their performances. In practice, we further extend CSPN in two aspects: 1) take sparse depth map as additional input, which is useful for the task of depth completion; 2) similar to commonly used 3D convolution operation in CNNs, we propose 3D CSPN to handle features with one additional dimension, which is effective in the task of stereo matching using 3D cost volume. For the tasks of sparse to dense, a.k.a depth completion. We experimented the proposed CPSN conjunct algorithms over the popular NYU v2 and KITTI datasets, where we show that our proposed algorithms not only produce high quality (e.g., 30% more reduction in depth error), but also run faster (e.g., 2 to 5x faster) than previous SOTA spatial propagation network. We also evaluated our stereo matching algorithm on the Scene Flow and KITTI Stereo datasets, and rank 1st on both the KITTI Stereo 2012 and 2015 benchmarks, which demonstrates the effectiveness of the proposed module. The code of CSPN proposed in this work will be released at https://github.com/XinJCheng/CSPN.

Zike Yan, Yuxin Tian, Xuesong Shi et al.

Recent advances have enabled a single neural network to serve as an implicit scene representation, establishing the mapping function between spatial coordinates and scene properties. In this paper, we make a further step towards continual learning of the implicit scene representation directly from sequential observations, namely Continual Neural Mapping. The proposed problem setting bridges the gap between batch-trained implicit neural representations and commonly used streaming data in robotics and vision communities. We introduce an experience replay approach to tackle an exemplary task of continual neural mapping: approximating a continuous signed distance function (SDF) from sequential depth images as a scene geometry representation. We show for the first time that a single network can represent scene geometry over time continually without catastrophic forgetting, while achieving promising trade-offs between accuracy and efficiency.

Bo Xu, Peng Wang, Yijia He et al.

Leveraging line features can help to improve the localization accuracy of point-based monocular Visual-Inertial Odometry (VIO) system, as lines provide additional constraints. Moreover, in an artificial environment, some straight lines are parallel to each other. In this paper, we designed a VIO system based on points and straight lines, which divides straight lines into structural straight lines (that is, straight lines parallel to each other) and non-structural straight lines. In addition, unlike the orthogonal representation using four parameters to represent the 3D straight line, we only used two parameters to minimize the representation of the structural straight line and the non-structural straight line. Furthermore, we designed a straight line matching strategy based on sampling points to improve the efficiency and success rate of straight line matching. The effectiveness of our method is verified on both public datasets of EuRoc and TUM VI benchmark and compared with other state-of-the-art algorithms.

Xinjing Cheng, Peng Wang, Yanqi Zhou et al.

Omnidirectional 360° camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view(FoV). However, corresponding 360° depth sensors, which are also critical for the perception system, are still difficult or expensive to have. In this paper, we propose a low-cost 3D sensing system that combines an omnidirectional camera with a calibrated projective depth camera, where the depth from the limited FoV can be automatically extended to the rest of the recorded omnidirectional image. To accurately recover the missing depths, we design an omnidirectional depth extension convolutional neural network(ODE-CNN), in which a spherical feature transform layer(SFTL) is embedded at the end of feature encoding layers, and a deformable convolutional spatial propagation network(D-CSPN) is appended at the end of feature decoding layers. The former resamples the neighborhood of each pixel in the omnidirectional coordination to the projective coordination, which reduces the difficulty of feature learning, and the later automatically finds a proper context to well align the structures in the estimated depths via CNN w.r.t. the reference image, which significantly improves the visual quality. Finally, we demonstrate the effectiveness of proposed ODE-CNN over the popular 360D dataset and show that ODE-CNN significantly outperforms (relatively 33% reduction in-depth error) other state-of-the-art (SoTA) methods.

Xinjing Cheng, Peng Wang, Chenye Guan et al.

Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resources needed at each pixel could be dynamically assigned upon requests. Specifically, we formulate the learning of the two hyper-parameters as an architecture selection problem where various configurations of kernel sizes and numbers of iterations are first defined, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-defined configurations at each pixel. In our experiments, we find weighted assembling can lead to significant accuracy improvements, which we referred to as "context-aware CSPN", while weighted selection, "resource-aware CSPN" can reduce the computational resource significantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w.r.t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++on the KITTI depth completion benchmark, where it significantly improves over CSPN and other SoTA methods.

Zhenheng Yang, Peng Wang, Yang Wang et al.

Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network has made significant process recently. Current state-of-the-art (SOTA) methods, are based on the learning framework of rigid structure-from-motion, where only 3D camera ego motion is modeled for geometry estimation.However, moving objects also exist in many videos, e.g. moving cars in a street scene. In this paper, we tackle such motion by additionally incorporating per-pixel 3D object motion into the learning framework, which provides holistic 3D scene flow understanding and helps single image geometry estimation. Specifically, given two consecutive frames from a video, we adopt a motion network to predict their relative 3D camera pose and a segmentation mask distinguishing moving objects and rigid background. An optical flow network is used to estimate dense 2D per-pixel correspondence. A single image depth network predicts depth maps for both images. The four types of information, i.e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered. We design various losses w.r.t. the two types of 3D motions for training the depth and motion networks, yielding further error reduction for estimated geometry. Finally, in order to solve the 3D motion confusion from monocular videos, we combine stereo images into joint training. Experiments on KITTI 2015 dataset show that our estimated geometry, 3D motion and moving object masks, not only are constrained to be consistent, but also significantly outperforms other SOTA algorithms, demonstrating the benefits of our approach.

Peng Wang, Ruigang Yang, Binbin Cao et al.

For applications such as autonomous driving, self-localization/camera pose estimation and scene parsing are crucial technologies. In this paper, we propose a unified framework to tackle these two problems simultaneously. The uniqueness of our design is a sensor fusion scheme which integrates camera videos, motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robustness and efficiency of the system. Specifically, we first have an initial coarse camera pose obtained from consumer-grade GPS/IMU, based on which a label map can be rendered from the 3D semantic map. Then, the rendered label map and the RGB image are jointly fed into a pose CNN, yielding a corrected camera pose. In addition, to incorporate temporal information, a multi-layer recurrent neural network (RNN) is further deployed improve the pose accuracy. Finally, based on the pose from RNN, we render a new label map, which is fed together with the RGB image into a segment CNN which produces per-pixel semantic label. In order to validate our approach, we build a dataset with registered 3D point clouds and video camera images. Both the point clouds and the images are semantically-labeled. Each video frame has ground truth pose from highly accurate motion sensors. We show that practically, pose estimation solely relying on images like PoseNet may fail due to street view confusion, and it is important to fuse multiple sensors. Finally, various ablation studies are performed, which demonstrate the effectiveness of the proposed system. In particular, we show that scene parsing and pose estimation are mutually beneficial to achieve a more robust and accurate system.

Xinyu Huang, Peng Wang, Xinjing Cheng et al.

Autonomous driving has attracted tremendous attention especially in the past few years. The key techniques for a self-driving car include solving tasks like 3D map construction, self-localization, parsing the driving road and understanding objects, which enable vehicles to reason and act. However, large scale data set for training and system evaluation is still a bottleneck for developing robust perception models. In this paper, we present the ApolloScape dataset [1] and its applications for autonomous driving. Compared with existing public datasets from real scenes, e.g. KITTI [2] or Cityscapes [3], ApolloScape contains much large and richer labelling including holistic semantic dense point cloud for each site, stereo, per-pixel semantic labelling, lanemark labelling, instance segmentation, 3D car instance, high accurate location for every frame in various driving videos from multiple sites, cities and daytimes. For each task, it contains at lease 15x larger amount of images than SOTA datasets. To label such a complete dataset, we develop various tools and algorithms specified for each task to accelerate the labelling process, such as 3D-2D segment labeling tools, active labelling in videos etc. Depend on ApolloScape, we are able to develop algorithms jointly consider the learning and inference of multiple tasks. In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving. We show that practically, sensor fusion and joint learning of multiple tasks are beneficial to achieve a more robust and accurate system. We expect our dataset and proposed relevant algorithms can support and motivate researchers for further development of multi-sensor fusion and multi-task learning in the field of computer vision.

Zhenheng Yang, Peng Wang, Yang Wang et al.

Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network is attracting significant attention. In this paper, we introduce a "3D as-smooth-as-possible (3D-ASAP)" prior inside the pipeline, which enables joint estimation of edges and 3D scene, yielding results with significant improvement in accuracy for fine detailed structures. Specifically, we define the 3D-ASAP prior by requiring that any two points recovered in 3D from an image should lie on an existing planar surface if no other cues provided. We design an unsupervised framework that Learns Edges and Geometry (depth, normal) all at Once (LEGO). The predicted edges are embedded into depth and surface normal smoothness terms, where pixels without edges in-between are constrained to satisfy the prior. In our framework, the predicted depths, normals and edges are forced to be consistent all the time. We conduct experiments on KITTI to evaluate our estimated geometry and CityScapes to perform edge evaluation. We show that in all of the tasks, i.e.depth, normal and edge, our algorithm vastly outperforms other state-of-the-art (SOTA) algorithms, demonstrating the benefits of our approach.

Yang Wang, Yi Yang, Zhenheng Yang et al.

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsupervised learning of optical flow methods. In this work we introduce a new method which models occlusion explicitly and a new warping way that facilitates the learning of large motion. Our method shows promising results on Flying Chairs, MPI-Sintel and KITTI benchmark datasets. Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.

Zhenheng Yang, Peng Wang, Wei Xu et al.

Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years. In this paper, we introduce a surface normal representation for unsupervised depth estimation framework. Our estimated depths are constrained to be compatible with predicted normals, yielding more robust geometry results. Specifically, we formulate an edge-aware depth-normal consistency term, and solve it by constructing a depth-to-normal layer and a normal-to-depth layer inside of the DCN. The depth-to-normal layer takes estimated depths as input, and computes normal directions using cross production based on neighboring pixels. Then given the estimated normals, the normal-to-depth layer outputs a regularized depth map through local planar smoothness. Both layers are computed with awareness of edges inside the image to help address the issue of depth/normal discontinuity and preserve sharp edges. Finally, to train the network, we apply the photometric error and gradient smoothness for both depth and normal predictions. We conducted experiments on both outdoor (KITTI) and indoor (NYUv2) datasets, and show that our algorithm vastly outperforms state of the art, which demonstrates the benefits from our approach.

Fangting Xia, Jun Zhu, Peng Wang et al.

Parsing human body into semantic regions is crucial to human-centric analysis. In this paper, we propose a segment-based parsing pipeline that explores human pose information, i.e. the joint location of a human model, which improves the part proposal, accelerates the inference and regularizes the parsing process at the same time. Specifically, we first generate part segment proposals with respect to human joints predicted by a deep model, then part- specific ranking models are trained for segment selection using both pose-based features and deep-learned part potential features. Finally, the best ensemble of the proposed part segments are inferred though an And-Or Graph. We evaluate our approach on the popular Penn-Fudan pedestrian parsing dataset, and demonstrate the effectiveness of using the pose information for each stage of the parsing pipeline. Finally, we show that our approach yields superior part segmentation accuracy comparing to the state-of-the-art methods.