让物理仿真支持复杂形状碰撞，实现从视频中精准反推物体属性
Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders
- 引入可微分碰撞处理机制，支持任意形状刚体交互
- 在非平面碰撞场景下仍能端到端优化物理属性
- 适配多种视觉重建方法，适合机器人与图形学研究者
从视频观测中同时识别物体的几何、外观和物理属性是一项具有挑战性的任务，广泛应用于机器人和计算机图形学。现有方法依赖全可微分的材料点法（MPM）与渲染技术，联合优化这些属性，但仅适用于平面碰撞器的简化交互，在物体与非平面表面碰撞时失效。本文提出AS-DiffMPM，一种可微分的MPM框架，支持任意形状碰撞器下的物理属性估计。该方法通过引入可微分碰撞处理机制，使目标物体能够与复杂刚体交互，同时保持端到端优化能力。我们证明，AS-DiffMPM可轻松集成至多种新型视图合成方法中，作为从视觉观测进行系统识别的通用框架。
原文摘要 · Abstract (English)
System identification involving the geometry, appearance, and physical properties from video observations is a challenging task with applications in robotics and graphics. Recent approaches have relied on fully differentiable Material Point Method (MPM) and rendering for simultaneous optimization of these properties. However, they are limited to simplified object-environment interactions with planar colliders and fail in more challenging scenarios where objects collide with non-planar surfaces. We propose AS-DiffMPM, a differentiable MPM framework that enables physical property estimation with arbitrarily shaped colliders. Our approach extends existing methods by incorporating a differentiable collision handling mechanism, allowing the target object to interact with complex rigid bodies while maintaining end-to-end optimization. We show AS-DiffMPM can be easily interfaced with various novel view synthesis methods as a framework for system identification from visual observations.
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。