About me
Hello, this is Hengli Wang. I got my Ph.D. degree from The Hong Kong University of Science and Technology (HKUST) in 2022, supervised by Prof. Ming Liu in RAM-LAB . Prior to this, I received my B.E. degree from Zhejiang University (ZJU) in 2018.
CV  / 
Github  / 
Google Scholar
|
Research
My research interest is mainly visual perception for autonomous driving. Specifically, I am working on the computation of visual features including stereo matching, optical flow estimation, and surface normal estimation. I am also focusing on improving the perception performance by exploiting the visual features, especially semantic segmentation in the image space and in the BEV space. Selected publications are shown as follows, and representative works are highlighted (* indicates equal contribution).
|
|
Stereo Matching: Fundamentals, State-of-the-Art, and Existing Challenges
Autonomous Driving Perception: Fundamentals and Applications, 2023
Chuang-Wei Liu, Hengli Wang, Sicen Guo, Mohammud J. Bocus, Qijun Chen, Rui Fan
bibtex
|
|
DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks
IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2022
Peide Cai, Hengli Wang, Yuxiang Sun, Ming Liu
arXiv /
bibtex /
project page
|
|
Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
IEEE Transactions on Cybernetics (T-CYB), 2021 (IF: 11.448)
Hengli Wang*, Rui Fan*, Yuxiang Sun, Ming Liu
arXiv /
bibtex /
project page
|
|
Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms
IEEE Transactions on Image Processing (T-IP), 2021 (IF: 10.856)
Rui Fan*, Hengli Wang*, Yuan Wang*, Ming Liu, Ioannis Pitas
arXiv /
bibtex /
code /
dataset
|
|
PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching
IEEE Robotics and Automation Letters (RA-L), 2021
presented at IEEE International Conference on Robotics and Automation (ICRA), 2021
Hengli Wang*, Rui Fan*, Peide Cai, Ming Liu
arXiv /
bibtex /
project page /
video
|
|
Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator
IEEE Robotics and Automation Letters (RA-L), 2021
presented at IEEE International Conference on Robotics and Automation (ICRA), 2021
Rui Fan*, Hengli Wang*, Bohuan Xue*, Huaiyang Huang, Yuan Wang, Ming Liu, Ioannis
Pitas
arXiv /
bibtex /
project page /
code /
dataset /
video
|
|
Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation
IEEE International Conference on Robotics and Automation (ICRA), 2021
Hengli Wang, Peide Cai, Yuxiang Sun, Lujia Wang, Ming Liu
arXiv /
bibtex /
project page /
video
|
|
S2P2: Self-Supervised Goal-Directed Path Planning Using RGB-D Data for Robotic Wheelchairs
IEEE International Conference on Robotics and Automation (ICRA), 2021
Hengli Wang, Yuxiang Sun, Rui Fan, Ming Liu
arXiv /
bibtex /
project page /
video
|
|
Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation
IEEE Transactions on Mechatronics (T-MECH), 2021 (IF: 5.673)
Rui Fan*, Hengli Wang*, Peide Cai, Jin Wu, Mohammud J. Bocus, Lei Qiao, Ming Liu
arXiv /
bibtex
|
|
SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Hengli Wang*, Rui Fan*, Peide Cai, Ming Liu
arXiv /
bibtex /
project page
|
|
DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Peide Cai, Hengli Wang, Yuxiang Sun, Ming Liu
arXiv /
bibtex /
project page /
video
|
|
Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
IEEE Robotics and Automation Letters (RA-L), 2021
presented at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Peide Cai, Hengli Wang, Huaiyang Huang, Yuxuan Liu, Ming Liu
arXiv /
bibtex /
project page /
video
|
|
The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods Transportation
IEEE Robotics and Automation Magazine (RAM), 2021
presented at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Tianyu Liu, Qinghai Liao, ..., Hengli Wang, ..., Ming Liu
arXiv /
bibtex /
project page /
video
|
|
CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised
Optical Flow Estimation
Conference on Robot Learning (CoRL), 2020 (34% acceptance rate)
Hengli Wang, Rui Fan, Ming Liu
arXiv /
bibtex /
project page /
video
|
|
Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for
Ground Mobile Robots
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
Hengli Wang*, Rui Fan*, Yuxiang Sun, Ming Liu
arXiv /
bibtex /
code
|
|
SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for
Accurate Freespace Detection
European Conference on Computer Vision (ECCV), 2020
Rui Fan*, Hengli Wang*, Peide Cai, Ming Liu
arXiv /
bibtex /
project page /
code /
dataset /
video
|
|
ATG-PVD: Ticketing Parking Violations on a Drone
European Conference on Computer Vision (ECCV) Workshops, 2020
Hengli Wang*, Yuxuan Liu*, Huaiyang Huang*, Yuheng Pan*, Wenbin Yu, Jialin Jiang,
Dianbin Lyu, Mohammud J. Bocus, Ming Liu, Ioannis Pitas, Rui Fan
arXiv /
bibtex /
project page /
dataset /
video
|
|
We Learn Better Road Pothole Detection: From Attention Aggregation to Adversarial
Domain Adaptation
European Conference on Computer Vision (ECCV) Workshops, 2020
Rui Fan*, Hengli Wang*, Mohammud J. Bocus, Ming Liu
arXiv /
bibtex /
project page /
code /
dataset
|
|
VTGNet: A Vision-Based Trajectory Generation Network for Autonomous Vehicles in
Urban Environments
IEEE Transactions on Intelligent Vehicles (T-IV), 2020
Peide Cai, Yuxiang Sun, Hengli Wang, Ming Liu
arXiv /
bibtex /
project page /
code /
dataset /
video
|
|
FuseSeg: Semantic Segmentation of Urban Scenes Based on RGB and Thermal Data Fusion
IEEE Transactions on Automation Science and Engineering (T-ASE), 2020
Yuxiang Sun, Weixun Zuo, Peng Yun, Hengli Wang, Ming Liu
pdf /
bibtex /
video
|
|
Self-Supervised Drivable Area and Road Anomaly Segmentation Using RGB-D Data for
Robotic Wheelchairs
IEEE Robotics and Automation Letters (RA-L), 2019
Hengli Wang, Yuxiang Sun, Ming Liu
arXiv /
bibtex /
code /
dataset
|
Service
- Journal review for IEEE T-PAMI, IEEE T-IP, IEEE T-RO, IEEE T-NNLS, IEEE T-ASE, IEEE T-ITS, IEEE T-IV, IEEE T-VT, IEEE T-IM, IEEE RA-L, IEEE SP-L, Pattern Recognition, Advanced Engineering Informatics, Journal of Systems Architecture, Neural Processing Letters, Engineering Applications of Artificial Intelligence, Multimedia Systems, Machine Vision and Applications, and The Visual Computer.
- Conference review for CVPR 2021-2023, ICCV 2021, 2023, ECCV 2022, 2024, AAAI 2023-2024, BMVC 2020-2023, ACCV 2024, ICIP 2021-2024, ICAS 2021, ICPR 2024, IROS 2019-2023, and ICRA 2019-2024.
- Technical program committee for the 1st AVVision Workshop in conjunction with WACV 2021, the 2nd AVVision Workshop in conjunction with ICCV 2021, the 3rd AVVision Workshop in conjunction with ECCV 2022, and special sessions in ICIP 2021, ICAS 2021 as well as IROS 2021.
|
|