profile photo

Hengli Wang (王恒立)

Ph.D. candidate
RAM-LAB
Department of Electronic and Computer Engineering
The Hong Kong University of Science and Technology

Email: hwangdf@connect.ust.hk

About me

Hello, I am Hengli Wang, a Ph.D. candidate of RAM-LAB in the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Ming Liu . I received my B.E. 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).

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-IP, IEEE T-NNLS, IEEE T-ITS, IEEE T-VT, IEEE T-IM, IEEE SP-L, and IEEE RA-L.
  • Conference review for AAAI 2023, ECCV 2022, ICCV 2021, CVPR 2021-2022, BMVC 2020-2022, ICIP 2021-2022, ICAS 2021, IROS 2019-2021, and ICRA 2019-2022.
  • 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.


Page template