iMatcher: Improve matching in point cloud registration via local-to-global geometric consistency learning
This addresses robust point cloud matching for computer vision applications like 3D reconstruction and robotics, representing a strong incremental improvement over existing methods.
The paper tackles point cloud registration by proposing iMatcher, a differentiable framework that uses local-to-global geometric consistency learning for feature matching, achieving state-of-the-art inlier ratios of 95%-97% on KITTI, 94%-97% on KITTI-360, and up to 81.1% on 3DMatch.
This paper presents iMatcher, a fully differentiable framework for feature matching in point cloud registration. The proposed method leverages learned features to predict a geometrically consistent confidence matrix, incorporating both local and global consistency. First, a local graph embedding module leads to an initialization of the score matrix. A subsequent repositioning step refines this matrix by considering bilateral source-to-target and target-to-source matching via nearest neighbor search in 3D space. The paired point features are then stacked together to be refined through global geometric consistency learning to predict a point-wise matching probability. Extensive experiments on real-world outdoor (KITTI, KITTI-360) and indoor (3DMatch) datasets, as well as on 6-DoF pose estimation (TUD-L) and partial-to-partial matching (MVP-RG), demonstrate that iMatcher significantly improves rigid registration performance. The method achieves state-of-the-art inlier ratios, scoring 95% - 97% on KITTI, 94% - 97% on KITTI-360, and up to 81.1% on 3DMatch, highlighting its robustness across diverse settings.