Quasi-newton solver for robust non-rigid registration

Yao, Yuxin, Deng, Bailin ORCID: https://orcid.org/0000-0002-0158-7670, Xu, Weiwei and Zhang, Juyong 2020. Quasi-newton solver for robust non-rigid registration. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 16-18 June 2020. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 7597-7606. 10.1109/CVPR42600.2020.00762

Preview	PDF - Accepted Post-Print Version Download (2MB) | Preview
Preview	PDF - Supplemental Material Download (7MB) | Preview

Abstract

Imperfect data (noise, outliers and partial overlap) and high degrees of freedom make non-rigid registration a classical challenging problem in computer vision. Existing methods typically adopt the $\ell_{p}$ type robust estimator to regularize the fitting and smoothness, and the proximal operator is used to solve the resulting non-smooth problem. However, the slow convergence of these algorithms limits its wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust estimator for data fitting and regularization, which can handle outliers and partial overlaps. We apply the majorization-minimization algorithm to the problem, which reduces each iteration to solving a simple least-squares problem with L-BFGS. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlap, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/Juyong/Fast_RNRR.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Publisher:	IEEE
ISBN:	9781728171685
Date of First Compliant Deposit:	30 March 2020
Date of Acceptance:	27 February 2020
Last Modified:	07 Nov 2022 09:56
URI:	https://orca.cardiff.ac.uk/id/eprint/130652

Citation Data

Cited 19 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item