Xinjing Cheng

Xinjing Cheng

Auto-generated profile, based on publicly available information

Xinjing Cheng

Robotics and Auto-driving Lab (RAL) Baidu Research

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 July 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XHXinyu Huang
Xinyu Huang
PWPeng Wang
Peng Wang
XCXinjing Cheng
Xinjing Cheng
DZDingfu Zhou
Dingfu Zhou
QGQichuan Geng
Qichuan Geng
RYRuigang Yang
Ruigang Yang
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 joint 3D-2D segment labeling, 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.

15 October 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XCXinjing Cheng
Xinjing Cheng
PWPeng Wang
Peng Wang
RYRuigang Yang
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. We can append this module to any output from a state-of-the-art (SOTA) network to improve their performances. In practice, we further extend CSPN in two aspects: 1) take a sparse depth map as additional input, which is useful for the task of sparse to dense (a.k.a depth completion); 2) 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 depth completion, we experimented the proposed CPSN conjunct algorithms over 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 5 × 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 again.

6 October 2018
Verified
Book Chapter
Closed access
PDF file
XCXinjing Cheng
Xinjing Cheng
PWPeng Wang
Peng Wang
RYRuigang Yang
Ruigang Yang

22 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
XCXinjing Cheng
Xinjing Cheng
PWPeng Wang
Peng Wang
CGChenye Guan
Chenye Guan
RYRuigang Yang
Ruigang Yang
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.

22 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
MLMingjia Li
Mingjia Li
BXBinhui Xie
Binhui Xie
Shuang LiShuang Li
Shuang Li
CLChi Harold Liu
Chi Harold Liu
XCXinjing Cheng
Xinjing Cheng
Generalizing models trained on normal visual conditions to target domains under adverse conditions is demanding in the practical systems. One prevalent solution is to bridge the domain gap between clear- and adverse-condition images to make satisfactory prediction on the target. However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality. Furthermore, most of them mainly focus on individual adverse condition such as nighttime or foggy, weakening the model versatility when encountering other adverse weathers. To overcome the above limitations, we propose a novel framework, Visibility Boosting and Logit-Constraint learning (VBLC), tailored for superior normal-to-adverse adaptation. VBLC explores the potential of getting rid of reference images and resolving the mixture of adverse conditions simultaneously. In detail, we first propose the visibility boost module to dynamically improve target images via certain priors in the image level. Then, we figure out the overconfident drawback in the conventional cross-entropy loss for self-training method and devise the logit-constraint learning, which enforces a constraint on logit outputs during training to mitigate this pain point. To the best of our knowledge, this is a new perspective for tackling such a challenging task. Extensive experiments on two normal-to-adverse domain adaptation benchmarks, i.e., Cityscapes -> ACDC and Cityscapes -> FoggyCityscapes + RainCityscapes, verify the effectiveness of VBLC, where it establishes the new state of the art. Code is available at https://github.com/BIT-DA/VBLC.