Reconstructing and simulating dynamic 3D scenes with both visual realism and physical consistency remains a fundamental challenge. Existing neural 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 3D Dynamic Convex Radiance Field that unifies visual rendering and physical simulation. PhysConvex represents deformable radiance fields using physically grounded 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 high-fidelity reconstruction of geometry, appearance, and physical properties from videos, outperforming existing methods.

翻译：在保持视觉真实感与物理一致性的前提下重建并仿真动态三维场景，仍然是一个基础性挑战。现有的神经表示方法，如 NeRF 和 3DGS，在表观重建方面表现出色，但难以捕捉复杂的材料形变与动力学行为。我们提出了 PhysConvex，一种物理信息三维动态凸体辐射场，它统一了视觉渲染与物理仿真。PhysConvex 使用基于连续介质力学原理的物理基础凸体基元来表示可形变的辐射场。我们引入了一种边界驱动的动态凸体表示，该表示通过顶点和表面动力学对形变进行建模，能够捕捉空间自适应、非均匀的形变以及演化的边界。为了高效仿真复杂几何与异质材料，我们进一步开发了一种降阶凸体仿真方法，该方法以神经蒙皮本征模态作为形状与材料感知的形变基，在牛顿动力学框架下使用时变降阶自由度对动态凸体场进行平流。凸体动力学还提供了紧凑、无间隙的体覆盖，从而同时提升了几何效率与仿真保真度。实验表明，PhysConvex 能够从视频中高保真地重建几何、表观及物理属性，其性能优于现有方法。