Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2009

Abstract

Most state-of-the-art nonrigid shape recovery methods usually use explicit deformable mesh models to regularize surface deformation and constrain the search space. These triangulated mesh models heavily relying on the quadratic regularization term are difficult to accurately capture large deformations, such as severe bending. In this paper, we propose a novel Gaussian process regression approach to the nonrigid shape recovery problem, which does not require to involve a predefined triangulated mesh model. By taking advantage of our novel Gaussian process regression formulation together with a robust coarse-to-fine optimization scheme, the proposed method is fully automatic and is able to handle large deformations and outliers. We conducted a set of extensive experiments for performance evaluation in various environments. Encouraging experimental results show that our proposed approach is both effective and robust to nonrigid shape recovery with large deformations.

Keywords

Shape, Gaussian processes, feature extraction, image matching, mesh generation, optimisation

Discipline

Computer Sciences | Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

2009 IEEE Conference on Computer Vision and Pattern Recognition CVPR: 20 - 25 June, Miami, FL

First Page

1319

Last Page

1326

ISBN

9781424439928

Identifier

10.1109/CVPR.2009.5206512

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2009.5206512

Download

Share

COinS