Metraipolis › archive › dc_9fe73f9dff15
Pair-Relative Partial Equivariance for Rotation-Robust Keypoint Descriptor Matching — arXiv:2611.02751
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02751
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:55:08.123Z
- SHA-256 of the archived text
509409993d9efacbc4987c1740a268b8aa72be5fb1f826dee8ec9a4e0d6dd49d- Stable URL of this page
https://metraipolis.com/documento/dc_9fe73f9dff15
How to cite
Pair-Relative Partial Equivariance for Rotation-Robust Keypoint Descriptor Matching — arXiv:2611.02751 — arXiv (en), https://arxiv.org/abs/2611.02751 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fe73f9dff15 (Metraipolis archive dc_9fe73f9dff15, sha256 509409993d9efacbc4987c1740a268b8aa72be5fb1f826dee8ec9a4e0d6dd49d)
BibTeX
@misc{dc9fe73f9dff15,
title = {Pair-Relative Partial Equivariance for Rotation-Robust Keypoint Descriptor Matching — arXiv:2611.02751},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02751},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fe73f9dff15; sha256 509409993d9efacbc4987c1740a268b8aa72be5fb1f826dee8ec9a4e0d6dd49d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02751. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learned keypoint descriptors trained on upright imagery often fail under large in-plane rotation. Steerers address this by applying a single exact SO(2) representation to the descriptor space, but this global group constraint can be too rigid for keypoint descriptors, whose angular responses need not follow a single group representation. We propose pair-relative partial equivariance, which measures equivariance under the empirical distribution of relative rotations in image pairs, and PaSteer, a relaxed descriptor-steering framework that allows the steering map to leave the exact representation manifold while retaining the lightweight, backbone-free design of steering. PaSteer instantiates this relaxation with two variants: an identity-preserving residual steerer (PaSteer-soft) and a free-form Fourier steerer (PaSteer-free). We show that the per-angle optimal linear steerer for a fixed non-equivariant descriptor generally does not obey the group composition law, explaining why exact representations can be suboptimal in the frozen-descriptor regime. On Roto-360, MegaDepth-1500, AIMS, and IMC-PT, PaSteer consistently improves rotation-robust matching over an exact steerer on frozen DeDoDe descriptors, especially under large relative rotations, with minimal upright degradation. 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) ; Computational Geometry (cs.CG). Pagina del lavoro: https://arxiv.org/abs/2611.02751 — 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 2026-11-03T18:16:53.019Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).