Progressive Correspondence Pruning by Consensus Learning
This work addresses the critical problem of robust correspondence selection for computer vision tasks, which is important for researchers and practitioners working on geometric vision problems.
This paper tackles the problem of correspondence selection, where the goal is to identify inliers from an initial set of putative matches that are often dominated by outliers. The authors propose a progressive pruning method using local-to-global consensus learning, which significantly outperforms state-of-the-art methods on robust line fitting, camera pose estimation, and retrieval-based image localization benchmarks.
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learning-based methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a ``pruning'' block that lets us identify reliable candidates among the initial matches according to consensus scores estimated using local-to-global dynamic graphs. We then achieve progressive pruning by stacking multiple pruning blocks sequentially. Our method outperforms state-of-the-arts on robust line fitting, camera pose estimation and retrieval-based image localization benchmarks by significant margins and shows promising generalization ability to different datasets and detector/descriptor combinations.