PUGS models underwater Gaussian motion as a distribution, not a single trajectory

arXivarXivPapers

PUGS models underwater Gaussian motion as a distribution, not a single trajectory
arXiv / Tingjun Li, Yuxi Wang and colleagues

Tingjun Li, Yuxi Wang, Guoqiang Zhong and Zhaoxiang Zhang present PUGS, a physics-guided uncertainty model for underwater dynamic 3D Gaussian Splatting. They argue that deterministic deformation fields break down underwater, where scattering, refraction, marine snow and low visibility make captured images physically ambiguous.

Instead of a single displacement, PUGS parameterizes each Gaussian’s motion as a probability distribution with an expected deformation and a physical uncertainty, and uses stochastic deformation optimization with local reparameterization to sample trajectories during training. Uncertainty stochastic annealing and a dual-path self-consistency distillation then convert that exploration into a deterministic reconstruction. The authors report improved rendering quality, temporal consistency and robustness on underwater dynamic datasets and physics-aware benchmarks.