Shengjun Zhang

I am a Ph.D student in the Department of Electronic Engineering at Tsinghua University, advised by Prof. Yueqi Duan. Before that, I obtained my B.Eng. in the Department of Engineering Physics, Tsinghua University. My research interest lie in 3D computer vision. Feel free to contact me if you are interested in our works or would like to work with us.

Email  /  Google Scholar  /  Github

*Equal contribution    ^†Project leader

In this paper, we propose Human Gaussian Graph (HGG) to generate generalizable and animatable Gaussian representations. We leverage the human structure prior to recover generalizable and animatable Gaussian representations

In this paper, we propose ScenePainter, a new framework for semantically consistent 3D scene generation, which aligns the outpainter's scene-specific prior with the comprehension of the current scene.

In this paper, we propose Scene Splatter, a momentum 3D scene generation paradigm to introduce existing scene information as momentum in the generation process, to balance the generative prior and scene consistency.

In this paper, we propose Gaussian Graph Network (GGN) to generate efficient and generalizable Gaussian representations.

In this paper, we propose geometry-to-voxel auxiliary learning to enable voxel representations to access point-level geometric information, which supports better generalisation of the voxel-based backbone with additional interpretations of multi-sensor point clouds.

In this paper, we propose Physics3D, a novel method for learning various physical properties of 3D objects through a video diffusion model. Our approach involves designing a highly generalizable physical simulation system based on a viscoelastic material model, which enables us to simulate a wide range of materials with high-fidelity capabilities.

Website Template