RGS-SLAM: ワンショット高密度初期化によるロバストなガウシアンスプラッティングSLAM
RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization
DINOv3特徴量と信頼度考慮のインライア分類器で密な多視点対応を一度に三角測量し、ガウシアンを初期配置することで、GS-SLAMの収束を約20%高速化しつつ高精細なマッピングを実現した。
著者: Wei-Tse Cheng, Yen-Jen Chiou, Yuan-Fu Yang
分類: cs.CV, cs.RO
原文アブストラクト
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/