AffineGlue: Joint Matching and Robust Estimation
This addresses the challenge of efficient and accurate feature matching in computer vision, particularly for real-world datasets, with incremental improvements over existing methods.
The paper tackles the problem of two-view feature matching and robust estimation by proposing AffineGlue, which reduces combinatorial complexity using single-point minimal solvers and a new homography solver with a gravity prior. It improves the AUC@10° score by 6.6 points on PhotoTourism compared to state-of-the-art methods and achieves similar accuracy to detector-free LoFTR on ScanNet.
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° 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.