ORCA
Online Research @ Cardiff

# Quasi-newton solver for robust non-rigid registration

 Yao, Yuxin, Deng, Bailin, 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,

 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) In Press Computer Science & Informatics Q Science > QA Mathematics > QA75 Electronic computers. Computer scienceQ Science > QA Mathematics > QA76 Computer software IEEE 30 March 2020 27 February 2020 16 Jun 2020 02:05 http://orca.cf.ac.uk/id/eprint/130652

### Actions (repository staff only)

 Edit Item

### Downloads

Downloads per month over past year

View more statistics