{"ID":2868042,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16909","arxiv_id":"2509.16909","title":"SLAM-Former: Putting SLAM into One Transformer","abstract":"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.","short_abstract":"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 t...","url_abs":"https://arxiv.org/abs/2509.16909","url_pdf":"https://arxiv.org/pdf/2509.16909v1","authors":"[\"Yijun Yuan\",\"Zhuoguang Chen\",\"Kenan Li\",\"Weibang Wang\",\"Hang Zhao\"]","published":"2025-09-21T04:04:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[\"Transformer\"]","has_code":false}