arXiv · 2611.18170
ALoMa: Affine Correspondences Beyond Patches
Abstract
Affine correspondences (ACs) enable robust and efficient solvers for multiple-view geometry by constraining the local geometry of point correspondences (PCs). Despite their utility in minimal solvers, AC estimation remains understudied. We revisit AC estimation beyond local image patches, extending it to the image and image-pair levels. Rather than estimating the components of the affine transformation separately, we learn the full 4-DoF matrix jointly. Building on this formulation, we introduce ALoMa, an AC estimator using LoMa keypoint descriptions, demonstrating consistent improvements across a wide range of downstream tasks. Code at https://github.com/davnords/loma.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
David Nordström, Georg Bökman, Viktor Larsson, Fredrik Kahl, Jonathan Ventura. 2026-11-13. ALoMa: Affine Correspondences Beyond Patches. https://searcharxiv.com/abs/2611.18170
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.