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.

我们提出了 AffineGlue，这是一种联合两视图特征匹配和鲁棒估计的方法，通过使用单点最小求解器减少问题的组合复杂性。AffineGlue 从一对多的对应中选择潜在匹配项来估计最小模型。引导匹配然后用于发现与模型一致的匹配，避免了一对一匹配的歧义。此外，我们推导出了一种新的最小求解器用于单应性矩阵估计，只需要一个仿射对应和重力先验。此外，我们训练了一个神经网络来排除不太可能导致良好模型的仿射对应。在真实数据集上，AffineGlue 优于 SOTA，即使假设重力方向向下。在 PhotoTourism 上，与 SOTA 相比，AUC@10° 的得分提高了 6.6 个点。在 ScanNet 上，AffineGlue 使 SuperPoint 和 SuperGlue 达到与无检测器的 LoFTR 相似的准确性。