Loading...
General discriminative optimization for point set registration
Zhao, Y. Tang, W. Feng, J. Wan, Tao Ruan Xi, L.
Zhao, Y.
Tang, W.
Feng, J.
Wan, Tao Ruan
Xi, L.
Publication Date
2022-02
End of Embargo
Supervisor
Rights
© 2022 Elsevier. Reproduced in accordance with the publisher's self-archiving policy. This manuscript version is made available under the CC-BY-NC-ND 4.0 license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Peer-Reviewed
Yes
Open Access status
openAccess
Accepted for publication
2021-11-04
Institution
Department
Awarded
Embargo end date
Additional title
Abstract
Point set registration has been actively studied in computer vision and graphics. Optimization algorithms are at the core of solving registration problems. Traditional optimization approaches are mainly based on the gradient of objective functions. The derivation of objective functions makes it challenging to find optimal solutions for complex optimization models, especially for those applications where accuracy is critical. Learning-based optimization is a novel approach to address this problem, which learns the gradient direction from datasets. However, many learning-based optimization algorithms learn gradient directions via a single feature extracted from the dataset, which will cause the updating direction to be vulnerable to perturbations around the data, thus falling into a bad stationary point. This paper proposes the General Discriminative Optimization (GDO) method that updates a gradient path automatically through the trade-off among contributions of different features on updating gradients. We illustrate the benefits of GDO with tasks of 3D point set registrations and show that GDO outperforms the state-of-the-art registration methods in terms of accuracy and robustness to perturbations.
Version
Accepted manuscript
Citation
Zhao Y, Tang W, Feng J et al (2022) General discriminative optimization for point set registration. Computers and Graphics. 102: 521-532.
Link to publisher’s version
Link to published version
Link to Version of Record
Type
Article