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).
Reconstructing and simulating dynamic scenes only from videos with both visual realism and physical consistency remains a fundamental challenge. Existing 3D representations, such as NeRFs and 3DGS, excel in appearance reconstruction but struggle to capture complex material deformation and dynamics. We propose PhysConvex, a Physics-informed Dynamic Convex Field that unifies visual reconstruction and physical simulation. PhysConvex represents deformable radiance fields using physically grounded 3D convex primitives governed by continuum mechanics. We introduce a boundary-driven dynamic convex representation that models deformation through vertex and surface dynamics, capturing spatially adaptive, non-uniform deformation, and evolving boundaries. To efficiently simulate complex geometries and heterogeneous materials, we further develop a reduced-order convex simulation that advects dynamic convex fields using neural skinning eigenmodes as shape- and material-aware deformation bases with time-varying reduced DOFs under Newtonian dynamics. Convex dynamics also offers compact, gap-free volumetric coverage, enhancing both geometric efficiency and simulation fidelity. Experiments demonstrate that PhysConvex achieves physically consistent dynamic reconstruction of geometry, appearance, and physical properties from videos, outperforming existing methods.
@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},
}