PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
This addresses the challenge of realistic motion synthesis for computer graphics and simulation applications, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of synthesizing novel motion in 3D scenes by integrating Newtonian dynamics into 3D Gaussians, achieving high-quality results across diverse materials like elastic entities and non-Newtonian fluids without requiring traditional meshing.
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 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 geometry embedding, highlighting the principle of "what you see is what you simulate (WS$^2$)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements. Our project page is at: https://xpandora.github.io/PhysGaussian/