
DN
David Nordstr\"om, Georg B\"okman, Viktor Larsson, Fredrik Kahl, Jonathan Ventura
· 1 min read
ResearcharXiv cs.CV
ALoMa: Affine Correspondences Beyond Patches
arXiv:2611.18170v1 Announce Type: new
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.
Original source
This story was published by arXiv cs.CV and written by David Nordstr\"om, Georg B\"okman, Viktor Larsson, Fredrik Kahl, Jonathan Ventura. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


