SOURCE-LINKED INTELLIGENCE

BayesianGS-SLAM: Uncertainty-Aware Neural Rendering SLAM via Probabilistic Formulation

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Neural-rendering-based SLAM relies on rendered RGB-D residuals for camera tracking and map optimization, but the reliability of these predictions can vary substantially because of sensor noise, limited observation coverage, and incomplete map representations. Without an explicit reliability estimate, unreliable residuals may adversely affect pose optimization, while frames already well explained by the current map may trigger redundant mapping updates. In this paper, we present BayesianGS-SLAM, an uncertainty-aware 3D Gaussian Splatting SLAM framework that estimates predictive color and depth

Read original source ↗ Open in workspace

recordType

paper

region

Global