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

profile photo
Preprints
dise Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
Fangfu Liu*, Hanyang Wang* Shunyu Yao , Shengjun Zhang, Jie Zhou, Yueqi Duan
arXiv, 2024
[arXiv] [Code] [Project Page]

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.

Publications
dise Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model
Shengjun Zhang, Jinzhao Li, Xin Fei, Hao Liu, Yueqi Duan
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Project Page]

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.

dise Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Shengjun Zhang, Xin Fei, Fangfu Liu, HaiXu Song, Yueqi Duan
Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2024
[arXiv] [Code] [Project Page]

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

dise GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds
Shengjun Zhang, Xin Fei, Yueqi Duan
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[arXiv] [Code]

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.


Website Template


© Shengjun Zhang | Last update: Mar. 1, 2025