VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping

TL;DR

VBGS-SLAM introduces a probabilistic framework for 3D scene modeling and camera tracking that maintains uncertainty estimates, improving robustness and reducing drift in SLAM applications.

Contribution

It couples splat map refinement with pose tracking using variational inference, enabling efficient updates and explicit uncertainty modeling.

Findings

Superior tracking performance in long sequences

Enhanced robustness against drift and challenging conditions

Efficient high-quality novel view synthesis across scenes

Abstract

3D Gaussian Splatting (3DGS) has shown promising results for 3D scene modeling using mixtures of Gaussians, yet its existing simultaneous localization and mapping (SLAM) variants typically rely on direct, deterministic pose optimization against the splat map, making them sensitive to initialization and susceptible to catastrophic forgetting as map evolves. We propose Variational Bayesian Gaussian Splatting SLAM (VBGS-SLAM), a novel framework that couples the splat map refinement and camera pose tracking in a generative probabilistic form. By leveraging conjugate properties of multivariate Gaussians and variational inference, our method admits efficient closed-form updates and explicitly maintains posterior uncertainty over both poses and scene parameters. This uncertainty-aware method mitigates drift and enhances robustness in challenging conditions, while preserving the efficiency and rendering quality of existing 3DGS. Our experiments demonstrate superior tracking performance and robustness in long sequence prediction, alongside efficient, high-quality novel view synthesis across diverse synthetic and real-world scenes.