PowerSim：基于幂图的微分物理仿真与渲染

中文摘要 AI 辅助

我们引入了PowerSim，一种将物理基础的、可微分的动力学引入到PowerFoam基于幂图的3D表示中的方法。PowerSim通过利用两者之间的自然对齐，直接将预训练的PowerFoam场景与物质点法（MPM）耦合：每个基元的几何和外观属性与MPM在物体变形时已经跟踪的量紧密对应。因此，模拟运动可以直接驱动场景的几何和外观，无需中间辅助表示。基于这一框架，我们在真实和合成场景上实现了一系列应用：（1）在用户交互下模拟静态场景，（2）恢复空间变化的材料场，（3）将独立捕获的场景中的基元合成到单个可模拟场景中，以及（4）光线追踪反射，随着物体变形而一致更新。我们的结果表明，PowerSim在物理基础的动力学方面优于以前的框架，同时解锁了独特优势，例如动态场景上的次级光线照明效果。结果最好在我们的项目网站上查看：此https URL。

英文摘要

We introduce PowerSim, a method to bring physically grounded, differentiable dynamics to PowerFoam's power diagram based 3D representation. PowerSim directly couples a pre-trained PowerFoam scene to the Material Point Method (MPM) by exploiting a natural alignment between the two: the geometric and appearance properties of each primitive correspond closely to the quantities MPM already tracks as an object deforms. Consequently, simulated motion can drive the scene's geometry and appearance directly, without an auxiliary representation in between. Built on this framework, we enable a range of applications on real and synthetic scenes: (1) simulating a static scene under user interaction, (2) recovering spatially varying material fields, (3) compositing primitives from independently captured scenes into a single simulation-ready scene and (4) ray-tracing reflections that update consistently as the object deforms. Our results suggest that PowerSim excels over previous frameworks for physically grounded dynamics, while unlocking unique advantages-such as secondary ray lighting effects on dynamic scenes. Results are best viewed on our project website: https://power-sim.github.io/.

发表机构

• Johns Hopkins University（约翰霍普金斯大学）

机构由 AI 辅助整理，请以论文原文为准。