RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization
This work addresses efficiency and robustness issues in SLAM systems for robotics and AR/VR applications, representing an incremental improvement over existing methods.
The paper tackles the problem of slow convergence and instability in Gaussian-splatting SLAM by introducing a one-shot dense initialization method, resulting in roughly 20% faster convergence and competitive or superior accuracy on TUM RGB-D and Replica datasets with real-time performance up to 925 FPS.
We introduce RGS-SLAM, a robust Gaussian-splatting SLAM framework that replaces the residual-driven densification stage of GS-SLAM with a training-free correspondence-to-Gaussian initialization. Instead of progressively adding Gaussians as residuals reveal missing geometry, RGS-SLAM performs a one-shot triangulation of dense multi-view correspondences derived from DINOv3 descriptors refined through a confidence-aware inlier classifier, generating a well-distributed and structure-aware Gaussian seed prior to optimization. This initialization stabilizes early mapping and accelerates convergence by roughly 20\%, yielding higher rendering fidelity in texture-rich and cluttered scenes while remaining fully compatible with existing GS-SLAM pipelines. Evaluated on the TUM RGB-D and Replica datasets, RGS-SLAM achieves competitive or superior localization and reconstruction accuracy compared with state-of-the-art Gaussian and point-based SLAM systems, sustaining real-time mapping performance at up to 925 FPS. Additional details and resources are available at this URL: https://breeze1124.github.io/rgs-slam-project-page/