Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration without Correspondences

Publisher:
IEEE
Publication Type:
Journal Article
Citation:
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, 00, pp. 11363-11371
Issue Date:
2020-01-01
Filename Description Size
09156354.pdfPublished version1.75 MB
Adobe PDF
Full metadata record
© 2020 IEEE. We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences. The advantage of the feature-metric projection error is robust to noise, outliers and density difference in contrast to the geometric projection error. Besides, minimising the feature-metric projection error does not need to search the correspondences so that the optimisation speed is fast. The principle behind the proposed method is that the feature difference is smallest if point clouds are aligned very well. We train the proposed method in a semi-supervised or unsupervised approach, which requires limited or no registration label data. Experiments demonstrate our method obtains higher accuracy and robustness than the state-of-the-art methods. Besides, experimental results show that the proposed method can handle significant noise and density difference, and solve both same-source and cross-source point cloud registration.
Please use this identifier to cite or link to this item: