Handi YIN

I'm a first year PhD student at ROAS Thrust, HKUST(GZ), in Guangzhou, China. Before that, I received my MPhil degree from CMA Thrust, HKUST(GZ) in 2024 and B.Eng. degree from Department of EE, Tsinghua University in 2022.

I'm currently supervised by Prof. Jie Song.

Email  /  Scholar  /  Github

profile photo

News

I will be presenting at SIGGRAPH Asia 2024 in Tokyo, Japan this December. If you're interested in my work, don't hesitate to reach out!

Research

My research mainly focuses on human pose prior and to utilize this prior for robotics sensing, controlling and motion planning.

EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System
Bonan Liu*, Handi Yin*, Manuel Kaufmann, Jinhao He, Sammy Christen, Jie Song^, Pan Hui
SIGGRAPH Asia 2024(TOG)
project page / video / arXiv

EgoHDM is an innovative online egocentric-inertial motion capture system that provides near real-time localization and dense scene mapping, enhancing human motion estimation in various terrains.

OmniColor: A Global Camera Pose Optimization Approach of LiDAR-360Camera Fusion for Colorizing Point Clouds
Bonan Liu, Guoyang Zhao, Jianhao Jiao, Guang Cai, Chengyang Li, Handi Yin, Yuyang Wang, Pan Hui^
ICRA 2024 Oral
code / video / arXiv

OmniColor colorizes point clouds with a 360-degree camera, optimizing camera poses for accurate image-to-geometry mapping without feature extraction, resulting in improved 3D reconstruction in robotic navigation and scene reconstruction tasks.