Siyuan Zhou 「周思远」

I am a third-year PhD student in the Department of Computing at The Hong Kong Polytechnic University, supervised by Prof. Bo Yang and co-supervised by Prof. Jing Li. Previously, I received my Bachelor of Science in Data Science and Technology from The Hong Kong University of Science and Technology with First Class Honors in 2023, under the supervision of Prof. Gary Shueng Han Chan. My research interests lie broadly in computer vision and machine learning. Currently, I focus on visual physics learning and reasoning.

Email  /  Github

profile photo

Publications
PhysInOne
Siyuan Zhou, Hejun Wang, Hu Cheng, Jinxi Li, Dongsheng Wang, Junwei Jiang, Yixiao Jin, Jiayue Huang, Shiwei Mao, Shangjia Liu, Yafei YANG, Hongkang Song, Shenxing Wei, Zihui Zhang, DataTeam vLAR, Bing WANG, Zhihua Wang, Chuhang Zou†, Bo Yang†
Conference on Computer Vision and Pattern Recognition (CVPR), 2026
project page / paper / code

We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems.

FreeGave demo FreeGave
Jinxi Li, Ziyang Song, Siyuan Zhou, Bo Yang*
Conference on Computer Vision and Pattern Recognition (CVPR), 2025
paper / code

FreeGave is a framework that learns 3D geometry, appearance and velocity purely from multi-view videos, achieving SOTA performance in future extrapolation task on four datasets.

RayletDF preview RayletDF
Shenxing Wei*, Jinxi Li*, Yafei Yang, Siyuan Zhou, Bo Yang
International Conference on Computer Vision (ICCV), 2025   (Highlight)
paper / code

We present a generalizable method for 3D surface reconstruction from raw point clouds or pre-estimated 3D Gaussians by 3DGS from RGB images.


Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.