Abstract | ||
---|---|---|
Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning techniques in this field, spatial consistency, which is essentially established by a Euclidean transformation between point clouds, has received almost no individual attention in existing learning frameworks. In this paper, we present PointDSC, a novel deep neural network that explicitly incorporates spatial consistency for pruning outlier correspondences. First, we propose a nonlocal feature aggregation module, weighted by both feature and spatial coherence, for feature embedding of the input correspondences. Second, we formulate a differentiable spectral matching module, supervised by pairwise spatial compatibility, to estimate the inlier confidence of each correspondence from the embedded features. With modest computation cost, our method outperforms the state-of-the-art handcrafted and learning-based outlier rejection approaches on several real-world datasets by a significant margin. We also show its wide applicability by combining PointDSC with different 3D local descriptors. [code release] |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPR46437.2021.01560 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 13 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bai Xuyang | 1 | 9 | 2.51 |
Zixin Luo | 2 | 32 | 4.43 |
Lei Zhou | 3 | 22 | 3.99 |
Hongkai Chen | 4 | 0 | 0.68 |
Lei Li | 5 | 0 | 0.34 |
Zeyu Hu | 6 | 0 | 1.35 |
Hongbo Fu | 7 | 1167 | 73.64 |
Chiew-Lan Tai | 8 | 1640 | 77.68 |