I am a Ph.D. student in Electrical and Computer Engineering at the University of Alberta, advised by Dr. Li Cheng and Dr. Xingyu Li.
My research focuses on 3D and 4D reconstruction and generation, particularly on recovering the shape, appearance, and motion of dynamic objects from monocular in-the-wild videos. Recently, I have been working on 4D animal reconstruction using 3D Gaussian Splatting.
Before starting my Ph.D., I worked at Tencent ARC on video understanding, depth estimation, and image enhancement. I received my M.Eng. from Harbin Institute of Technology through a joint graduate program with Southern University of Science and Technology (SUSTech), and my B.Eng. from SUSTech.
A progressive test-time optimization framework for reconstructing high-fidelity 4D animals from a single monocular video. The method disentangles articulated pose and non-rigid deformation, generalizing across species with strong visual fidelity.
Check my Google Scholar page for the most up-to-date list.
Siyuan Li, Weiying Chen, Yilin Wang, Xinxin Zuo, Xingyu Li, Li Cheng
European Conference on Computer Vision (ECCV), 2026 Oral (Spotlight)
Weiying Chen, Yuchong Gao, Siyuan Li, Marek Reformat, Rui Zheng, Edmond Lou
European Conference on Computer Vision (ECCV), 2026
Paper and project page coming soon
Ye Liu, Siyuan Li, Yang Wu, Chang Wen Chen, Ying Shan, Xiaohu Qie
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Siyuan Li, Yue Luo, Ye Zhu, Xun Zhao, Yu Li, Ying Shan
Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
Siyuan Li, Qingsha S. Cheng, Jianguo Zhang
IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2020
