Haoang Li

Welcome to my homepage! I am Haoang Li (pronounced as "Horn Lee"). I am currently an Assistant Professor at The Hong Kong University of Science and Technology (Guangzhou).

My research interest lies in 3D computer vision and robot navigation. I solve problems based on both optimization algorithms and deep learning.

Previously, I mainly focused on geometric SLAM and 3D reconstruction. In the future, along with my students, we will work on the following directions:

SLAM in dynamic scenes with humans and other dynamic objects (based on neural network and geometric constraints; considering kinetics/geometric priors);
3D scene/object reconstruction and rendering (based on neural network; considering geometric priors and/or semantic information);
Embodied AI, e.g., vision-and-language navigation (integration with some robotics techniques such as SLAM);
AI-generated content, e.g., data synthesis for autonomous driving (based on diffusion and rendering)
Large-scale place recognition and localization (based on neural network and geometric constraints);
Multi/cross-modal 3D computer vision tasks, such as semantic occupancy prediction and bird's eye view (BEV) feature extraction (based on neural network);

I am looking for Ph.D. students, Research Assistants, and Interns/Visiting Students. For details, please refer to this [document] (currently only in Chinese; I will provide an English version in the future).

Email: haoang.li.cuhk@gmail.com (I may fail to reply to your email in time due to the relatively heavy workload recently. I will get back to you as soon as possible. Thank you for your understanding!)

Experience

Assistant Professor, Thrust of Robotics and Autonomous Systems, The Hong Kong University of Science and Technology (Guangzhou), February 2024 - Present

Leader of Intelligent Robot Perception and Navigation (IRPN) Lab

Postdoc, Department of Informatics, Technical University of Munich, August 2022 – February 2024

Supervisor: Prof. Daniel Cremers

Ph.D., Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, August 2018 – July 2022

Supervisor: Prof. Yun-Hui Liu

Visiting Ph.D., Department of Computer Science, ETH Zurich, November 2021 – February 2022

Supervisor: Prof. Marc Pollefeys

M.Eng., School of Remote Sensing and Information Engineering, Wuhan University, September 2016 – June 2018

Supervisor: Prof. Jian Yao

B.Eng., School of Remote Sensing and Information Engineering, Wuhan University, September 2012 – June 2016

Publications (selected)

Please refer to Google Scholar for the full publication list. The download links of codes and/or datasets are available in the papers.

"J": Journal, "C": Conference, "*": Co-first authorship

Computer Vision

[C7] Haoang Li*, Jinghu Dong*, Binghui Wen*, Ming Gao*, Tianyu Huang, Yun-Hui Liu, and Daniel Cremers, "DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates," in IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

[J3] Haoang Li, Ji Zhao, Jean-Charles Bazin, Pyojin Kim, Kyungdon Joo, Zhenjun Zhao, and Yun-Hui Liu, "Hong Kong World: Leveraging Structural Regularity for Line-based SLAM," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.

[C6] Tianyu Huang*, Haoang Li*, Kejing He, Congying Sui, Bin Li, and Yun-Hui Liu, "Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

[J2] Haoang Li, Ji Zhao, Jean-Charles Bazin, and Yun-Hui Liu, "Quasi-globally Optimal and Near/True Real-time Vanishing Point Estimation in Manhattan World," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.

[C5] Wen Chen*, Haoang Li*, Qiang Nie, and Yun-Hui Liu, "Deterministic Point Cloud Registration via Novel Transformation Decomposition," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

[C4] Haoang Li*, Kai Chen*, Pyojin Kim, Kuk-Jin Yoon, Zhe Liu, Kyungdon Joo, and Yun-Hui Liu, "Learning Icosahedral Spherical Probability Map Based on Bingham Mixture Model for Vanishing Point Estimation," IEEE/CVF International Conference on Computer Vision (ICCV), 2021.

[C3] Haoang Li, Kai Chen, Ji Zhao, Jiangliu Wang, Pyojin Kim, Zhe Liu, and Yun-Hui Liu, "Learning to Identify Correct 2D-2D Line Correspondences on Sphere," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[J1] Haoang Li, Ji Zhao, Jean-Charles Bazin, and Yun-Hui Liu, "Robust Estimation of Absolute Camera Pose via Intersection Constraint and Flow Consensus," IEEE Transactions on Image Processing (TIP), 2020.

[C2] Haoang Li, Pyojin Kim, Ji Zhao, Kyungdon Joo, Zhipeng Cai, Zhe Liu, and Yun-Hui Liu, "Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World," European Conference on Computer Vision (ECCV), 2020.

[C1] Haoang Li, Ji Zhao, Jean-Charles Bazin, Wen Chen, Zhe Liu, and Yun-Hui Liu, "Quasi-globally Optimal and Efficient Vanishing Point Estimation in Manhattan World," IEEE/CVF International Conference on Computer Vision (ICCV), oral presentation, 2019.

Robotics

[C6] Haoang Li, Wen Chen, Ji Zhao, Jean-Charles Bazin, Lei Luo, Zhe Liu, and Yun-Hui Liu, "Robust and Efficient Estimation of Absolute Camera Pose for Monocular Visual Odometry," IEEE International Conference on Robotics and Automation (ICRA), 2020.

[C5] Haoang Li, Ji Zhao, Jean-Charles Bazin, Wen Chen, Kai Chen, and Yun-Hui Liu, "Line-based Absolute and Relative Camera Pose Estimation in Structured Environments," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.

[C4] Haoang Li, Yazhou Xing, Ji Zhao, Jean-Charles Bazin, Zhe Liu, and Yun-Hui Liu, "Leveraging Structural Regularity of Atlanta World for Monocular SLAM," IEEE International Conference on Robotics and Automation (ICRA), 2019.

[C3] Haoang Li, Ji Zhao, Jean-Charles Bazin, Lei Luo, Junlin Wu, and Jian Yao, "Robust Camera Pose Estimation via Consensus on Ray Bundle and Vector Field," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018.

[C2] Haoang Li, Jian Yao, Jean-Charles Bazin, Xiaohu Lu, Yazhou Xing, and Kang Liu, "A Monocular SLAM System Leveraging Structural Regularity in Manhattan World," IEEE International Conference on Robotics and Automation (ICRA), 2018.

[C1] Haoang Li, Jian Yao, Xiaohu Lu, and Junlin Wu, "Combining Points and Lines for Camera Pose Estimation and Optimization in Monocular Visual Odometry," IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017.

Awards (selected)

Outstanding Reviewer Award at CVPR 2021
Outstanding Tutor Award of Faculty of Engineering, The Chinese University of Hong Kong
Excellent Tutor Award of Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong
Postgraduate Scholarship of The Chinese University of Hong Kong
First-class Postgraduate Scholarship of Wuhan University
Excellent Undergraduate Dissertation of Hubei Province, China

Professional Services

Reviewer for CVPR 2020 -- 2022, ICCV 2021, ECCV 2022, ICRA 2019 -- 2022, IROS 2019 -- 2022 etc.