Metraipolis › archive › dc_d13ed574cdb5
Ray-SCR: Generalizing Scene Coordinate Regression Across Camera Models — arXiv:2611.03098
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03098
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:55:18.658Z
- SHA-256 of the archived text
74e9166c3447aa9512f067206aff14ab7e81b7cdfec9a925889aa895e5c8889d- Stable URL of this page
https://metraipolis.com/documento/dc_d13ed574cdb5
How to cite
Ray-SCR: Generalizing Scene Coordinate Regression Across Camera Models — arXiv:2611.03098 — arXiv (en), https://arxiv.org/abs/2611.03098 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d13ed574cdb5 (Metraipolis archive dc_d13ed574cdb5, sha256 74e9166c3447aa9512f067206aff14ab7e81b7cdfec9a925889aa895e5c8889d)
BibTeX
@misc{dcd13ed574cdb5,
title = {Ray-SCR: Generalizing Scene Coordinate Regression Across Camera Models — arXiv:2611.03098},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03098},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d13ed574cdb5; sha256 74e9166c3447aa9512f067206aff14ab7e81b7cdfec9a925889aa895e5c8889d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03098. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Among visual localization strategies, scene coordinate regression (SCR) has emerged as an attractive approach for its compactness, accuracy, and speed. Despite these advantages, SCR models generalize poorly across substantially different camera models, such as omnidirectional or strongly rectified imagery. This limitation arises because, changes in field of view, lens distortion, or rectification-induced resampling can make the same scene content appear differently depending on its pixel position, degrading localization accuracy. To cope with this limitation, we introduce Ray-SCR, a lightweight extension to existing SCR architectures that conditions local visual features on their calibrated viewing rays and refines neighboring ray-conditioned features with a shallow local Transformer. We further formulate supervision directly in ray space and use sparse SfM points as metric anchors that link observations across views and camera models. Taken together, these components enable a single scene representation built from a panoramic mapping sequence to accurately localize query images captured with very different cameras, including pinhole, fisheye, and omnidirectional cameras. We evaluate Ray-SCR across multiple SCR architectures and on datasets with pinhole, fisheye, and omnidirectional cameras. The proposed ray conditioning substantially improves generalization across cameras and leads to state-of-the-art localization performance in these challenging cross-camera settings. The project page is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.03098 — 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 2026-11-03T18:16:53.047Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).