ALoMa Paper Extends Affine Correspondence Estimation Beyond Patches
Researchers from Chalmers and others published ALoMa, extending affine correspondence estimation from local patches to image level using LoMa/LightGlue descriptors, reducing errors to single digits. The paper also shows empirically that the Frobenius norm is a poor loss function for this task.
2026-11-17 ~ 2026-11-17 · 2 related posts
- ALoMa paper extends affine correspondence estimation to image-pair level, cutting error to single digits — ducha_aiki · 2026-11-17
- ALoMa: Frobenius norm is a bad loss for affine correspondences, Charbonnier cuts error 3x — ducha_aiki · 2026-11-17