Decoupling Motion and Geometry in 4D Gaussian Splatting

TL;DR

VeGaS introduces a velocity-based 4D Gaussian Splatting framework that decouples motion and geometry, enabling more accurate modeling of complex dynamic scenes.

Contribution

The paper proposes a novel velocity-based framework with a Galilean shearing matrix and a geometric deformation network to improve 4D Gaussian Splatting.

Findings

Achieves state-of-the-art performance on public datasets.

Effectively models complex non-linear motions.

Reduces visual artifacts in dynamic scene reconstruction.

Abstract

High-fidelity reconstruction of dynamic scenes is an important yet challenging problem. While recent 4D Gaussian Splatting (4DGS) has demonstrated the ability to model temporal dynamics, it couples Gaussian motion and geometric attributes within a single covariance formulation, which limits its expressiveness for complex motions and often leads to visual artifacts. To address this, we propose VeGaS, a novel velocity-based 4D Gaussian Splatting framework that decouples Gaussian motion and geometry. Specifically, we introduce a Galilean shearing matrix that explicitly incorporates time-varying velocity to flexibly model complex non-linear motions, while strictly isolating the effects of Gaussian motion from the geometry-related conditional Gaussian covariance. Furthermore, a Geometric Deformation Network is introduced to refine Gaussian shapes and orientations using spatio-temporal context and velocity cues, enhancing temporal geometric modeling. Extensive experiments on public datasets demonstrate that VeGaS achieves state-of-the-art performance.