AI RESEARCH
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
arXiv CS.CV
•
ArXi:2603.09668v1 Announce Type: new Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio-temporal variability of wind, as well as the complex deformations of objects. We present DiffWind, a physics-informed differentiable framework that unifies wind-object interaction modeling, video-based reconstruction, and forward simulation. Specifically, we represent wind as a grid-based physical field and objects as particle systems derived from 3D Gaussian Splatting, with their interaction modeled by the Material Point Method.