Metraipolis › archive › dc_84b267eef049
CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching — arXiv:2611.03932
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03932
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:05:00.407Z
- SHA-256 of the archived text
efa3f98425d2270b9be7da05c3d41507f426d431fd8b57a78957e28c8ad2fca7- Stable URL of this page
https://metraipolis.com/documento/dc_84b267eef049
How to cite
CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching — arXiv:2611.03932 — arXiv (en), https://arxiv.org/abs/2611.03932 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84b267eef049 (Metraipolis archive dc_84b267eef049, sha256 efa3f98425d2270b9be7da05c3d41507f426d431fd8b57a78957e28c8ad2fca7)
BibTeX
@misc{dc84b267eef049,
title = {CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching — arXiv:2611.03932},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03932},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84b267eef049; sha256 efa3f98425d2270b9be7da05c3d41507f426d431fd8b57a78957e28c8ad2fca7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03932. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feature matching underpins many robotic perception tasks, including visual localization, mapping, SLAM, and autonomous navigation. Existing semi-dense matchers predict confidence on fixed grids, limiting correspondences to predefined locations and requiring costly high-resolution grids for precise localization. We present CoReMatch (Coordinate Refinement Match), a recurrent framework that refines correspondences directly in continuous coordinate space rather than predicting discrete confidence maps. CoReMatch progressively improves correspondence estimates by propagating information across iterations. At the coarse stage, a Deep Aggregated Transformer captures global context and iteratively updates correspondence coordinates, while a lightweight regression head further sharpens their localization. Experiments on indoor and outdoor benchmarks show that CoReMatch strikes a strong balance between accuracy and efficiency, outperforming Efficient LoFTR in accuracy while running more than 10x faster on embedded edge hardware. These results demonstrate that recurrent coordinate refinement offers an efficient and scalable approach to real-time feature matching for robotic perception. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.03932 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T18:39:37.593Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).