Decoupling Motion and Geometry in 4D Gaussian Splatting

2026-03-01

AI Summary

Existing 4D Gaussian splatting methods couple motion and geometry within a single covariance representation, making it difficult to model complex dynamics and often leading to visual artifacts. This work proposes VeGaS, a novel framework that explicitly decouples motion and geometry in 4D Gaussian splatting for the first time. Motion is characterized through a Galilean shear matrix that models time-varying velocity, while a geometric deformation network leverages spatiotemporal context to refine the shape and orientation of Gaussians. Evaluated on public benchmarks, VeGaS significantly outperforms current state-of-the-art methods, effectively reducing artifacts and enabling more accurate reconstruction of complex, nonlinear dynamic scenes.

Technology Category

• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• 4D Gaussian Splatting
• motion-geometry coupling
• dynamic scene reconstruction
• visual artifacts
• temporal dynamics

Innovation

• 4D Gaussian Splatting
• motion-geometry decoupling
• Galilean shearing
• velocity-based modeling
• Geometric Deformation Network