A robust loss for point cloud registration

Deng, Zhi ORCID: https://orcid.org/0000-0002-0158-7670, Yao, Yuxin, Deng, Bailin ORCID: https://orcid.org/0000-0002-0158-7670 and Zhang, Juyong 2021. A robust loss for point cloud registration. Presented at: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Virtual, 11-17 October 2021. 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

PDF - Accepted Post-Print Version Download (11MB)

Abstract

The performance of surface registration relies heavily on the metric used for the alignment error between the source and target shapes. Traditionally, such a metric is based on the point-to-point or point-to-plane distance from the points on the source surface to their closest points on the target surface, which is susceptible to failure due to instability of the closest-point correspondence. In this paper, we propose a novel metric based on the intersection points between the two shapes and a random straight line, which does not assume a specific correspondence. We verify the effectiveness of this metric by extensive experiments, including its direct optimization for a single registration problem as well as unsupervised learning for a set of registration problems. The results demonstrate that the algorithms utilizing our proposed metric outperform the state-of-the-art optimization-based and unsupervised learning-based methods.

Item Type:	Conference or Workshop Item (Paper)
Status:	In Press
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Date of First Compliant Deposit:	17 September 2021
Date of Acceptance:	22 July 2021
Last Modified:	09 Nov 2022 11:32
URI:	https://orca.cardiff.ac.uk/id/eprint/143694

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item