GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-08 · 45 (8) · 9806-9821
DOI: 10.1109/tpami.2023.3259038 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-08. Verfasst von Zheng Qin und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Algorithms, Acceleration. Die Arbeit wurde bisher 308-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by 18 ∼ 31 percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Qin, Z., Yu, H., Wang, C., Guo, Y., Peng, Y., Ilic, S., Hu, D., & Xu, K. (2023). GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 9806-9821. https://doi.org/10.1109/tpami.2023.3259038
Vancouver
Qin Z, Yu H, Wang C, Guo Y, Peng Y, Ilic S, et al. GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(8):9806-9821. doi:10.1109/tpami.2023.3259038
BibTeX
@article{Qin2023,
author = {Qin, Zheng and Yu, Hao and Wang, Changjian and Guo, Yulan and Peng, Yuxing and Ilic, Slobodan and Hu, Dewen and Xu, Kai},
title = {GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {8},
pages = {9806--9821},
doi = {10.1109/tpami.2023.3259038}
}
EUVIMED