PhysConvex: Physics-Informed Dynamic Convex Fields for Reconstruction and Simulation

Dan Wang1, Xinrui Cui 2, Serge Belongie3 Ravi Ramamoorthi1
1University of California, San Diego 2University of North Texas 3University of Copenhagen
arXiv
Model visualization

PhysConvex introduces boundary-driven dynamic convex fields integrated with mesh-free reduced-order convex simulation for dynamic reconstruction, system identification(a), physical generalization(b,c). It recovers appearance, geometry, and physics from videos, improving dynamic and physical reconstruction(d,e), training efficiency(f).

Abstract

Reconstructing deformable objects from video requires a 4D representation that should preserve geometry, explain motion through physics, and generalize to future or new physical conditions. Existing dynamic NeRF and Gaussian methods achieve strong view synthesis, yet their voxel or ellipsoidal primitives are primarily designed for appearance rendering and typically driven by centers or predefined particle bindings, limiting physically meaningful non-uniform deformation and sharp boundary evolution. We present PhysConvex, a physics-informed dynamic convex field for video-based reconstruction, physical system identification, and simulation. PhysConvex represents a dynamic object as material-space deformable convex primitives whose boundary is advected by physical dynamics. The boundary-driven convex expresses non-uniform deformation and evolving active supports while serving simultaneously as a rendering element, deformation carrier, and physical support where mass, elastic response, forces, and contacts are evaluated. We further introduce a mesh-free reduced-order convex simulator in which neural skinning modes define physics-based deformation bases directly over deformable convex supports. Experiments show improved dynamic and physical reconstruction, efficiency, future prediction, and generalization to changed materials, forces, and boundary conditions.

PhysConvex Framework

Model visualization

PhysConvex proposes differentiable boundary-driven dynamic convex field and mesh-free reduced-order convex simulation, jointly reconstructing geometry, appearance, and physical properties of dynamic objects.

Dynamic Reconstruction

Generalization to Novel Forces

Generalization to New Materials

BibTeX

@misc{wang2026physconvexphysicsinformed3ddynamic,
      title={PhysConvex: Physics-Informed 3D Dynamic Convex Radiance Fields for Reconstruction and Simulation}, 
      author={Dan Wang and Xinrui Cui and Serge Belongie and Ravi Ramamoorthi},
      year={2026},
      eprint={2602.18886},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2602.18886}, 
}