RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918291023331328 |
|---|---|
| author | Cheng, Wei-Tse Chiou, Yen-Jen Yang, Yuan-Fu |
| author_facet | Cheng, Wei-Tse Chiou, Yen-Jen Yang, Yuan-Fu |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00705 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization Cheng, Wei-Tse Chiou, Yen-Jen Yang, Yuan-Fu Computer Vision and Pattern Recognition Robotics 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/ |
| title | RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2601.00705 |