SOURCE-LINKED INTELLIGENCE

PhysReal: Learning Real-World Deformable Object Physics via Hybrid Constitutive Modeling

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Learning physically plausible dynamics from visual observations is essential for interactive world models and embodied agents. However, modeling real-world deformable objects remains challenging because their dynamics often arise from complex, spatially heterogeneous material responses. To address this challenge, we propose PhysReal, a video-driven framework for learning and simulating the underlying physics of real deformable objects. PhysReal integrates a spatially varying hybrid expert-neural constitutive model with a differentiable MPM simulator and 3DGS renderer. Analytical expert models

Read original source ↗ Open in workspace

recordType

paper

region

Global