Research Analyzer
← Back ICRA 2026

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

Yuhan Zhu, Yanyu Zhang, Jie Xu, Wei Ren

PDF

AI summary

Key figure (auto-extracted from paper)
VBGS-SLAM replaces deterministic optimization in 3D Gaussian Splatting SLAM with a probabilistic framework that jointly tracks camera pose and scene geometry while explicitly modeling uncertainty.
Variational Bayesian Inference 3D Gaussian Splatting Probabilistic SLAM Uncertainty Quantification Real-time Reconstruction Closed-form Updates

Problem

Current 3DGS-based SLAM systems rely on deterministic gradient optimization, making them sensitive to initialization, prone to catastrophic forgetting, and computationally heavy for long sequences. They also lack a principled way to quantify uncertainty in poses and map parameters.

Approach

The method formulates SLAM as a generative probabilistic model where camera poses and Gaussian map parameters are treated as latent variables. It uses variational Bayesian inference with conjugate priors to derive closed-form updates that jointly optimize the map and pose while propagating uncertainty.

Key results

  • State-of-the-art tracking accuracy and robustness on long sequences
  • Efficient closed-form updates outperform gradient-based optimization pipelines
  • High-quality novel view synthesis across synthetic and real-world datasets
  • Explicit uncertainty modeling mitigates drift and catastrophic forgetting

Why it matters

Enables more reliable and efficient real-time 3D reconstruction and localization for robotics and autonomous systems by replacing fragile deterministic optimization with principled uncertainty quantification.

Abstract

3D Gaussian Splatting (3DGS) has shown promis- ing results for 3D scene modeling using mixtures of Gaus- sians, 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 genera- tive 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 effi- ciency 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.

Index terms

Probabilistic Inference Localization Mapping

Related papers