用智能填充与自适应优化，让3D高斯模型快速模拟物理动态。
FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization
- 通过蒙特卡洛采样填充内部粒子，保持几何精度。
- 1分钟内完成高保真物理仿真，仅需7GB内存。
- 适合需要快速真实感动态模拟的科研与工业场景。
将3D高斯点阵（3DGS）扩展至4D物理仿真仍具挑战。现有基于材料点法（MPM）的方法或依赖人工调参，或从视频扩散模型中蒸馏动力学，限制了泛化能力与优化效率。近期使用大语言模型（LLMs）/视觉语言模型（VLMs）的方法存在文本/图像到3D的感知鸿沟，导致物理行为不稳定，且常忽略3DGS的表面结构，引发不合理的运动。本文提出FastPhysGS，一种快速稳健的物理驱动动态3DGS仿真框架：(1) 基于蒙特卡洛重要性采样（MCIS）的实例感知粒子填充（IPF），高效填充内部粒子同时保留几何保真度；(2) 双向图解耦优化（BGDO），一种自适应策略，可快速优化由VLM预测的材料参数。实验表明，FastPhysGS在仅7 GB运行内存下，1分钟内实现高保真物理仿真，显著优于先前方法，具有广泛应用潜力。
原文摘要 · Abstract (English)
Extending 3D Gaussian Splatting (3DGS) to 4D physical simulation remains challenging. Based on the Material Point Method (MPM), existing methods either rely on manual parameter tuning or distill dynamics from video diffusion models, limiting the generalization and optimization efficiency. Recent attempts using LLMs/VLMs suffer from a text/image-to-3D perceptual gap, yielding unstable physics behavior. In addition, they often ignore the surface structure of 3DGS, leading to implausible motion. We propose FastPhysGS, a fast and robust framework for physics-based dynamic 3DGS simulation:(1) Instance-aware Particle Filling (IPF) with Monte Carlo Importance Sampling (MCIS) to efficiently populate interior particles while preserving geometric fidelity; (2) Bidirectional Graph Decoupling Optimization (BGDO), an adaptive strategy that rapidly optimizes material parameters predicted from a VLM. Experiments show FastPhysGS achieves high-fidelity physical simulation in 1 minute using only 7 GB runtime memory, outperforming prior works with broad potential applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。