CVPR 2025 Best Paper Candidate (14/13008), ICCV Doctoral Consortium Award, third place in ICRA RoboDrive Challenge, CVPR Outstanding Reviewer Award, etc. Selected publications: 'PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments' (IEEE Transactions on Robotics); 'Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World' (CVPR); 'Large-Scale LiDAR-Based Loop Closing via Combination of Equivariance and Invariance on SE(3)' (IEEE/ASME Transactions on Mechatronics); 'G2-SDF: Geometry-Guided Neural Signed Distance Fields for Scalable and Detailed Reconstruction' (IEEE Robotics and Automation Letters); 'Accelerating Vision-language-action Model Integrated with Action Chunking via Parallel Decoding' (IROS); 'Interactive Navigation for Legged Manipulators with Learned Arm-Pushing Controller' (IROS); 'RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation' (IEEE).
Research Experience
Assistant Professor, Thrust of Robotics and Autonomous Systems/Intelligent Transportation, 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.
Education
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.
Background
Research interests lie in 3D computer vision and robotics. Current research directions include: Embodied AI (such as vision-language action/manipulation, vision-language navigation, humanoid perception and control), AI-generated content (such as 3D/4D scene synthesis), and 3D/4D reconstruction and rendering (such as Gaussian splatting/NeRF, dynamic SLAM, human avatar). Closely collaborating with Prof. Hesheng Wang from Shanghai Jiao Tong University.
Miscellany
Continuously looking for Ph.D. students, Research Assistants, and Interns/Visiting Students working on the above directions.