PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams

arXiv:2609.38153 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://power-sim.github.io

Terminology

• Gaussian Splatting — 6× in this paper · explained in 4 episodes
• Ablation — 5× in this paper · explained in 1 episode
• 3D Gaussian Splatting — 4× in this paper · explained in 2 episodes
• Material Point Method — 4× in this paper
• Ablation Studies — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Anisotropy — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Google Scanned Object — 2× in this paper
• Grounding — 2× in this paper · explained in 3 episodes
• Segmentation Masks — 2× in this paper · explained in 2 episodes
• ACM Transactions on Graphics — 1× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• In Computer Vision and Pattern Recognition — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Segment and Track Anything
• DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors
• Gradient-Driven 3D Segmentation and Affordance Transfer in Gaussian Splatting Using 2D Masks
• Segment Anything
• Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels
• PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
• Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models