VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping
This addresses robustness issues in SLAM for 3D scene modeling, though it appears incremental as it builds on existing 3DGS methods.
The paper tackled the problem of 3D Gaussian Splatting SLAM being sensitive to initialization and prone to forgetting by proposing VBGS-SLAM, a variational Bayesian framework that couples map refinement and pose tracking, resulting in superior tracking performance and robustness in long sequences while maintaining efficiency and rendering quality.
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.