Click here to flash read.
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.