AffineGlue: Joint Matching and Robust Estimation
Abstract
We propose AffineGlue, a method for joint two-view feature matching and robust estimation that reduces the combinatorial complexity of the problem by employing single-point minimal solvers. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches. Moreover, we derive a new minimal solver for homography estimation, requiring only a single affine correspondence (AC) and a gravity prior. Furthermore, we train a neural network to reject ACs that are unlikely to lead to a good model. AffineGlue is superior to the SOTA on real-world datasets, even when assuming that the gravity direction points downwards. On PhotoTourism, the AUC@10{\deg} score is improved by 6.6 points compared to the SOTA. On ScanNet, AffineGlue makes SuperPoint and SuperGlue achieve similar accuracy as the detector-free LoFTR.
Cite
@article{arxiv.2307.15381,
title = {AffineGlue: Joint Matching and Robust Estimation},
author = {Daniel Barath and Dmytro Mishkin and Luca Cavalli and Paul-Edouard Sarlin and Petr Hruby and Marc Pollefeys},
journal= {arXiv preprint arXiv:2307.15381},
year = {2023}
}