PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
UCLA Health · Zhejiang University · +1 more institution
Abstract
We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthe-sis. Employing a custom 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…
Citation impact
- FWCI
- 66.77
- Percentile
- 100%
- References
- 54
Authors
7Topics & keywords
- Generative grammar
- Dynamics (music)
- Computer science
- Physics
- Statistical physics
- Artificial intelligence