VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM

TL;DR

VarSplat introduces an uncertainty-aware 3D Gaussian Splatting SLAM system that explicitly models per-splat appearance variance, improving robustness and accuracy in diverse real-world scenes.

Contribution

It presents a novel uncertainty-aware approach that explicitly learns per-splat appearance variance and uses it to guide SLAM processes, enhancing stability and performance.

Findings

Improves robustness in low-texture and reflective regions.

Achieves superior tracking and mapping results.

Provides competitive novel view synthesis quality.

Abstract

Simultaneous Localization and Mapping (SLAM) with 3D Gaussian Splatting (3DGS) enables fast, differentiable rendering and high-fidelity reconstruction across diverse real-world scenes. However, existing 3DGS-SLAM approaches handle measurement reliability implicitly, making pose estimation and global alignment susceptible to drift in low-texture regions, transparent surfaces, or areas with complex reflectance properties. To this end, we introduce VarSplat, an uncertainty-aware 3DGS-SLAM system that explicitly learns per-splat appearance variance. By using the law of total variance with alpha compositing, we then render differentiable per-pixel uncertainty map via efficient, single-pass rasterization. This map guides tracking, submap registration, and loop detection toward focusing on reliable regions and contributes to more stable optimization. Experimental results on Replica (synthetic) and TUM-RGBD, ScanNet, and ScanNet++ (real-world) show that VarSplat improves robustness and achieves competitive or superior tracking, mapping, and novel view synthesis rendering compared to existing studies for dense RGB-D SLAM.