VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel OptimizationJailing Lin, Shu Jiang, Qingyuan Zeng, Zhenzhong Wang, Min Jianghttps://arxiv.org/abs/2508.13792
VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel OptimizationThe intrinsic dynamics of an object governs its physical behavior in the real world, playing a critical role in enabling physically plausible interactive simulation with 3D assets. Existing methods have attempted to infer the intrinsic dynamics of objects from visual observations, but generally face two major challenges: one line of work relies on manually defined constitutive priors, making it difficult to generalize to complex scenarios; the other models intrinsic dynamics using neural networ…