mlsanityData to 14 Oct 2026

PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams

arXiv 2609.38153 ↗First posted 29 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

28 of 37 references.

References · 28

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  4. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  5. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  6. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
  7. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
  8. 2023Segment and Track Anythingcited by 193
  9. 2024PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generationcited by 191
  10. 2023Segment Any 3D Gaussianscited by 161
  11. 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identificationcited by 154
  12. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 139
16 more
  1. 2024Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussianscited by 97
  2. 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splattingcited by 88
  3. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 87
  4. 2024Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusioncited by 80
  5. 2024FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimallycited by 58
  6. 2024GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulationcited by 49
  7. 2025Radiant Foam: Real-Time Differentiable Ray Tracingcited by 34
  8. 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamicscited by 32
  9. 2025Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixelscited by 24
  10. 2025Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulationcited by 20
  11. 2025MeshSplatting: Differentiable Rendering with Opaque Meshescited by 20
  12. 2024Gradient-Driven 3D Segmentation and Affordance Transfer in Gaussian Splatting Using 2D Maskscited by 4
  13. 2024Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splattingcited by 4
  14. 2025LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentationcited by 3
  15. 2026Power Foam: Unifying Real-Time Differentiable Ray Tracing and Rasterizationcited by 3
  16. 2026Semantic Foam: Unifying Spatial and Semantic Scene Decompositioncited by 1

Built on by

Not cited yet.