Decoupling Motion and Geometry in 4D Gaussian Splatting
This work improves dynamic scene reconstruction for applications like computer vision and graphics, representing an incremental advance by refining an existing method to handle complex motions more effectively.
The paper tackles the problem of high-fidelity reconstruction of dynamic scenes by addressing limitations in 4D Gaussian Splatting, which couples motion and geometry, leading to visual artifacts; the proposed VeGaS framework decouples these aspects using a velocity-based approach and achieves state-of-the-art performance on public datasets.
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.