|
Yushuo Chen I'm currently a 3rd-year Ph.D. student from Tsinghua University, advised by Prof. Yebin Liu. Previously, I received my bachlor's degree at Yao Class, IIIS, advised by Prof. Li Yi. My research interests lie in Computer Vision and Graphics, especially in the field of digital humans. Currently, I'm focusing on dynamic human modeling and understanding. Feel free to reach out for any topics! |
portrait: makoto @ Rhinz |
News
|
Research |
|
DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective
Yushuo Chen, Ruizhi Shao, Youxin Pang, Hongwen Zhang, Xinyi Wu, Rihui Wu, Yebin Liu arXiv Preprint, 2025 arXiv We present a novel framework to reconstruct human avatars from monocular videos with high-fidelity and high-quality details, by generating the human motions from alternative perspective as an additional supervision signal. |
|
Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling
Cheng Peng*, Jingxiang Sun*, Yushuo Chen, Zhaoqi Su, Zhuo Su, Yebin Liu arXiv Preprint, 2025 Project Page / Code / arXiv
We present the Parametric Gaussian Human Model (PGHM), a generalizable and efficient framework that integrates human priors into 3DGS for fast and high-fidelity avatar reconstruction from monocular videos.
|
|
MeshAvatar: Learning High-quality Triangular
Human Avatars from Multi-view Videos
Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, Yebin Liu ECCV, 2024 Project Page / Code / arXiv / Video We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos, enabling direct use to downstream grphical pipelines. |
|
Last update on September 2025.
|