SLAM-Former: Putting SLAM into One Transformer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918144988151808 |
|---|---|
| author | Yuan, Yijun Chen, Zhuoguang Li, Kenan Wang, Weibang Zhao, Hang |
| author_facet | Yuan, Yijun Chen, Zhuoguang Li, Kenan Wang, Weibang Zhao, Hang |
| contents | We present SLAM-Former, a novel neural approach that integrates full SLAM capabilities into a single transformer. Similar to traditional SLAM systems, SLAM-Former comprises both a frontend and a backend that operate in tandem. The frontend processes sequential monocular images in real-time for incremental mapping and tracking, while the backend performs global refinement to ensure a geometrically consistent result. This alternating execution allows the frontend and backend to mutually promote one another, enhancing overall system performance. Comprehensive experimental results demonstrate that SLAM-Former achieves superior or highly competitive performance compared to state-of-the-art dense SLAM methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16909 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SLAM-Former: Putting SLAM into One Transformer Yuan, Yijun Chen, Zhuoguang Li, Kenan Wang, Weibang Zhao, Hang Computer Vision and Pattern Recognition Robotics We present SLAM-Former, a novel neural approach that integrates full SLAM capabilities into a single transformer. Similar to traditional SLAM systems, SLAM-Former comprises both a frontend and a backend that operate in tandem. The frontend processes sequential monocular images in real-time for incremental mapping and tracking, while the backend performs global refinement to ensure a geometrically consistent result. This alternating execution allows the frontend and backend to mutually promote one another, enhancing overall system performance. Comprehensive experimental results demonstrate that SLAM-Former achieves superior or highly competitive performance compared to state-of-the-art dense SLAM methods. |
| title | SLAM-Former: Putting SLAM into One Transformer |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2509.16909 |