I'm a third-year PhD student in Computer Science at Zhejiang University, advised by Prof. Xiaowei Zhou.
I obtained my bachelor's degree in Computer Science from Zhejiang University in 2022.
My current research focuses on:
3D/4D neural reconstruction and rendering, and volumetric videos
.
More places where you can find me:
GitHub,
Twitter (X),
Google Scholar and
[email protected]
[CVPR 2025] FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction
*Denotes equal contribution. Project page and more demos coming soon!
[CVPR 2025] StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
*Denotes equal contribution. Street video model.
[CVPR 2025] EnvGS: Modeling View-Dependent Appearance with Environment Gaussian
*Denotes equal contribution. Our work on reconstructing reflective Gaussians.
[SIGGRAPH Asia 2024 (TOG)] Representing Long Volumetric Video with Temporal Gaussian Hierarchy
*Denotes equal contribution. Our latest project on long volumetric video!
Level of Gaussians: Real-Time View Synthesis for Large Scenes with Millions of Square Meters
Expansive Gaussian reconstruction with Level-of-Detail.
[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution
My recent project on real-time volumetric videos, check it out and leave a star 😎!
[CVPR 2024] Relightable and Animatable Neural Avatar from Sparse-View Video
Another recent project on animatable and relightable digital humans.
[SIGGRAPH Asia 2023 (TC)] EasyVolcap: Accelerating Neural Volumetric Video Research
Our neural volumetric video framework, check it out and leave a star 😎!
[CVPR 2023] Learning Neural Volumetric Representations of Dynamic Humans in Minutes
*Denotes equal contribution.
[SIGGRAPH Asia 2022 (Conf)] Efficient Neural Radiance Fields for Interactive Free-viewpoint Video
*Denotes equal contribution.