用物理模拟视频研究动态推演，发现代码生成更稳定，扩散模型更准但不靠谱。
MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics
- 用代码生成和视频扩散两种方法模拟物理行为
- 代码生成能稳定外推，但难从视觉推参数；扩散模型识形准但结果不物理
- 适合对物理仿真与视频生成交叉感兴趣的学者
为研究从视频中推断物理动态并向前外推的能力，我们构建了一个包含2D材料点法（MPM）物理模拟的数据库，涵盖柔性物体、流体、运动物体及发射源等丰富物理现象。我们在该数据集上评估了代码生成与视频扩散方法，通过改变物理相关辅助信息的数量，分析其优劣。代码生成模型不仅实现了MPM模拟的自动合成，还揭示了其从视觉输入中推断物理参数存在困难，但相比视频扩散模型，能产生更物理合理且时间稳定的外推结果；而视频扩散模型更能准确识别几何特征，却导致物理上不合理的预测。
原文摘要 · Abstract (English)
To study the ability to infer physical dynamics from videos and extrapolate them forward in time, we assemble a dataset of 2D Material Point Method (MPM) physical simulations covering rich physical phenomena such as deformable objects, fluids, kinetic objects, and emitters. We study code generation and video diffusion approaches on this dataset, identifying their strengths and weaknesses by varying the amount of physically relevant side information. The code generation model, beyond giving a working demonstration of automatic synthesis of MPM simulations, reveals that such an approach struggles with inferring physical parameters from visual input, but relative to video diffusion, produces physically and temporally stable extrapolations forward in time, while the video diffusion model more strongly identifies geometric properties from visual input but produces physically implausible extrapolations.
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。