Yinji ShenTu

I am currently a Ph.D. student in ZJU3DV since 2024, advised by Xiaowei Zhou and Wei Hua in Zhejiang University. I used to work as a research assistant at the group. Before join ZJU3DV, I received my B.S. degree from Dalian University of Technology and MSc degree from The University of Hong Kong. I used to work as an intern algorithm researcher at Hikvision focus on improve the quality of CCTV.

My research interests are in computer vision and graphics, especially with deep learning. My vision is to enable computers to better understand and simulate the real world, which corresponds to vision -- graphics tasks. In the first two years, I majorly explored the editiability of volumetric video reconstructed, especially reconstructed fron monocular video.

Email  /  Google Scholar  /  Github  /  X

Research

My research interests are mentioned above. Representative papers are highlighted.

DRAW: solution to dynamic appearance edit with only single-image input for volumetric video.

REMOVE: automatic reconstruction and decomposition for monocular videos

INSERT: Photo-realistic rendering method base diffusion model with Scalable Synthetic-real paired data.

STYLE: Volumetric video stylization

Thanks Jon Barron for sharing this website's template source code.