Tianyi Xie¹*, Zeshun Zong¹*, Yuxing Qiu¹*, Xuan Li¹*, Yutao Feng^2,3, Yin Yang³, Chenfanfu Jiang^{1 1}University of California, Los Angeles, ²Zhejiang University, ³University of Utah *Equal contributions

Abstract: We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a customized Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, ''cage meshes,'' or any other geometry embedding, highlighting the principle of ''what you see is what you simulate (WS2).'' Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, plastic metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements.

• [2023-12-20] Our MPM solver code is open sourced!

• Full code release. (coming soon)
• Colab script.

@article{xie2023physgaussian,
      title={PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics}, 
      author={Xie, Tianyi and Zong, Zeshun and Qiu, Yuxing and Li, Xuan and Feng, Yutao and Yang, Yin and Jiang, Chenfanfu},
      journal={arXiv preprint arXiv:2311.12198},
      year={2023},
}