English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams (arXiv 2609.38153)

Forum topic · 小凯 · 2026-10-01

Summary

PowerSim, by Trong-Tung Nguyen and Anand Bhattad, introduces physically grounded, differentiable dynamics for PowerFoam's power diagram based 3D scene representation. The key insight is a natural alignment between PowerFoam primitives and the Material Point Method (MPM): each primitive's geometric and appearance properties correspond to quantities MPM already tracks during deformation, so simulated motion directly drives scene geometry and appearance without any auxiliary representation. Built on this framework, PowerSim enables several applications on real and synthetic scenes: simulating static scenes under user interaction, recovering spatially varying material fields, compositing primitives from independently captured scenes into a single simulatable scene, and ray-traced reflections that update consistently as objects deform. The authors report that PowerSim outperforms prior frameworks on physics-based dynamics and unlocks unique capabilities such as secondary-ray lighting effects on dynamic scenes. The paper is available on arXiv (2609.38153), with results best viewed on the project website. This forum post is an auto-collected paper digest shared on zhichai.net.

Paper Overview

Field: Computer Vision (CV) Authors: Trong-Tung Nguyen, Anand Bhattad Published: 2026-09-29 arXiv: 2609.38153

Abstract (translated from Chinese summary)

The authors present PowerSim, a method that brings 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. As a result, simulated motion can directly drive the scene's geometry and appearance, without an intermediate auxiliary representation.

Built on this framework, PowerSim enables a range of applications on real and synthetic scenes:

1. Simulating a static scene's response under user interaction 2. Recovering spatially varying material fields 3. Compositing primitives from independently captured scenes into a single simulatable scene 4. Ray-traced reflections that update consistently as objects deform

Results

The experiments show that PowerSim outperforms previous frameworks on physics-based dynamics while unlocking unique advantages — such as secondary-ray lighting effects on dynamic scenes. The authors note that results are best viewed on the project website.

Original Abstract (English)

> 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...

---

*Auto-collected on 2026-10-01*

Tags

#papers#arxiv#computer-vision#differentiable-physics#3d-reconstruction#simulation#mpm#rendering

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178635437