PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xie, Tianyi, Zong, Zeshun, Qiu, Yuxing, Li, Xuan, Feng, Yutao, Yang, Yin, Jiang, Chenfanfu
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909168761307136
author Xie, Tianyi
Zong, Zeshun
Qiu, Yuxing
Li, Xuan
Feng, Yutao
Yang, Yin
Jiang, Chenfanfu
author_facet Xie, Tianyi
Zong, Zeshun
Qiu, Yuxing
Li, Xuan
Feng, Yutao
Yang, Yin
Jiang, Chenfanfu
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2311_12198
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
Xie, Tianyi
Zong, Zeshun
Qiu, Yuxing
Li, Xuan
Feng, Yutao
Yang, Yin
Jiang, Chenfanfu
Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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/
title PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
topic Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2311.12198