Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.05738 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917353851191296 |
|---|---|
| author | Thirgood, Christopher Mendez, Oscar Ling, Erin Storey, Jon Hadfield, Simon |
| author_facet | Thirgood, Christopher Mendez, Oscar Ling, Erin Storey, Jon Hadfield, Simon |
| contents | We present a real-time tracking SLAM system that unifies efficient camera tracking with photorealistic feature-enriched mapping using 3D Gaussian Splatting (3DGS). Our main contribution is integrating dense feature rasterization into the novel-view synthesis, aligned with a visual foundation model. This yields strong semantics, going beyond basic RGB-D input, aiding both tracking and mapping accuracy. Unlike previous semantic SLAM approaches (which embed pre-defined class labels) FeatureSLAM enables entirely new downstream tasks via free-viewpoint, open-set segmentation. Across standard benchmarks, our method achieves real-time tracking, on par with state-of-the-art systems while improving tracking stability and map fidelity without prohibitive compute. Quantitatively, we obtain 9\% lower pose error and 8\% higher mapping accuracy compared to recent fixed-set SLAM baselines. Our results confirm that real-time feature-embedded SLAM, is not only valuable for enabling new downstream applications. It also improves the performance of the underlying tracking and mapping subsystems, providing semantic and language masking results that are on-par with offline 3DGS models, alongside state-of-the-art tracking, depth and RGB rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05738 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time Thirgood, Christopher Mendez, Oscar Ling, Erin Storey, Jon Hadfield, Simon Computer Vision and Pattern Recognition We present a real-time tracking SLAM system that unifies efficient camera tracking with photorealistic feature-enriched mapping using 3D Gaussian Splatting (3DGS). Our main contribution is integrating dense feature rasterization into the novel-view synthesis, aligned with a visual foundation model. This yields strong semantics, going beyond basic RGB-D input, aiding both tracking and mapping accuracy. Unlike previous semantic SLAM approaches (which embed pre-defined class labels) FeatureSLAM enables entirely new downstream tasks via free-viewpoint, open-set segmentation. Across standard benchmarks, our method achieves real-time tracking, on par with state-of-the-art systems while improving tracking stability and map fidelity without prohibitive compute. Quantitatively, we obtain 9\% lower pose error and 8\% higher mapping accuracy compared to recent fixed-set SLAM baselines. Our results confirm that real-time feature-embedded SLAM, is not only valuable for enabling new downstream applications. It also improves the performance of the underlying tracking and mapping subsystems, providing semantic and language masking results that are on-par with offline 3DGS models, alongside state-of-the-art tracking, depth and RGB rendering. |
| title | FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.05738 |