About Me

I am a second-year Ph.D. student at the CSE Department, the Chinese University of Hong Kong (CUHK), supervised by Prof. Chi-Wing FU, Philip. I received my Master’s degree at the School of Information and Communication Engineering from the University of Electronic Science and Technology of China (UESTC), supervised by Prof. Guanghui LIU and Prof. Shuaicheng LIU. Before that, I got my Bachelor’s degree from Sichuan University (SCU). My research interests include 3D registration, 3D point cloud representation, and 3D hand mesh reconstruction.

News

• 2023.07:   One paper is accepted to ICCV 2023.
• 2023.03:   One paper is accepted to CVPR 2023.

Publications

2023

SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Suyi Chen*, Hao Xu*, Ru Li, Guanghui Liu, Chi-Wing Fu, Shuaicheng Liu (* Joint first author)

Paper | Video | Code | BibTex

H2ONet: Hand-Occlusion-and-Orientation-aware Network for Real-time 3D Hand Mesh Reconstruction

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023

Hao Xu, Tianyu Wang, Xiao Tang, Chi-Wing Fu

Paper | Video | Code | BibTex

2022

FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022

Hao Xu, Nianjin Ye, Guanghui Liu, Bing Zeng, Shuaicheng Liu

Paper | Video | Code | BibTex

2021

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Hao Xu, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng

Paper | Video | Code | BibTex

Education

• 2022.08 - Present, Ph.D. candidate, The Chinese University of Hong Kong (CUHK)
• 2019.09 - 2022.06, M.Sc., University of Electronic Science and Technology of China (UESTC)
• 2015.09 - 2019.06, B.E., Sichuan University (SCU)

Experience

• 2018.12 - 2022.06, Intern, Megvii Research

Projects

• 2018.12 - 2019.07, Driver Monitor System (DMS)

Design a light-weighted end-to-end network running on an onboard chip to detect smoking, phoning, and drinking in driving.

• 2019.07 - 2020.03, NIO Gaze Estimation

Design a light-weighted end-to-end network running on an onboard chip to estimate gaze and detect eye closure and occlusion at the same time.