PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D Gaussians

2026-09-07

AI Summary

该研究提出PhysMAS框架，通过多代理协作解决复杂场景下4D高斯合成问题，无需逐场景反向传播，实现高效且物理合理的动态场景生成。

Abstract

Efficient, fully automatic, and physically plausible 4D Gaussian synthesis is an important goal for dynamic scene generation. Recent physics-based methods couple 3D Gaussians with the Material Point Method (MPM) to generate physically driven motion, but extending this paradigm to heterogeneous multi-part objects and interacting multi-object scenes remains challenging. Object-level physical assignment collapses distinct parts into a single material state, while one-shot predictions from large language models, vision-language models, or agents neither reliably bind different materials to identified parts nor verify that the resulting MPM configuration is executable. Score Distillation Sampling (SDS)-based parameter optimization, meanwhile, requires repeated per-scene score evaluations and gradient backpropagation, incurring lengthy optimization and potentially yielding suboptimal or unstable solutions. We therefore present PhysMAS, a physics-grounded multi-agent framework. From a motion prompt and four scene views, an Object-Part Scene Agent establishes persistent identities and calls a Material Reasoning Agent for part-wise profiles. It invokes solver-aware skills to bind these identities and profiles to per-particle MPM fields and execute all objects in a shared domain; the framework then screens candidate forward-simulation results. This supports heterogeneous multi-part and interacting multi-object scenes without per-scene diffusion-score backpropagation. Extensive experiments demonstrate that, compared with recent physics-based 4D Gaussian baselines that rely on SDS, PhysMAS achieves better semantic alignment and perceived physical plausibility while requiring less runtime.

Problem

• 4D Gaussian synthesis
• heterogeneous multi-part objects
• interacting multi-object scenes
• Material Point Method (MPM)

Innovation

• Physics-Grounded
• Multi-Agent Framework
• Material Point Method (MPM)
• Score Distillation Sampling (SDS)
• Scene Synthesis