SOURCE-LINKED INTELLIGENCE

Wind on Trees: Testing Physical Grounding in Dynamic 4D Gaussian Splatting

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Monocular reconstruction of wind-driven vegetation is severely underconstrained: motion along the viewing direction is largely unobservable, a moving canopy offers few reliable correspondences, and nearly the entire scene is dynamic, providing little static reference. Directly-learned deformation fields in 4D Gaussian Splatting therefore optimize photometric consistency rather than recover the motion that produced it. We replace that field with a physically parameterized deformation prior: one damped harmonic oscillator per rigid part, driven by the observed wind and integrated by differentiab

Read original source ↗ Open in workspace

recordType

paper

region

Global