Show simple item record

dc.contributor.authorZhao, Y.
dc.contributor.authorTang, W.
dc.contributor.authorFeng, J.
dc.contributor.authorWan, Tao Ruan
dc.contributor.authorXi, L.
dc.date.accessioned2022-03-26T13:36:44Z
dc.date.accessioned2022-03-30T10:19:51Z
dc.date.available2022-03-26T13:36:44Z
dc.date.available2022-03-30T10:19:51Z
dc.date.issued2022-02
dc.identifier.citationZhao Y, Tang W, Feng J et al (2022) General discriminative optimization for point set registration. Computers and Graphics. 102: 521-532.
dc.identifier.urihttp://hdl.handle.net/10454/18830
dc.descriptionYes
dc.description.abstractPoint 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.
dc.language.isoenen
dc.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/)
dc.subjectPoint set registration
dc.subjectSupervised learning
dc.subjectLearning-based optimisation
dc.titleGeneral discriminative optimization for point set registration
dc.status.refereedYes
dc.date.application2021-11-17
dc.typeArticle
dc.type.versionAccepted manuscript
dc.identifier.doihttps://doi.org/10.1016/j.cag.2021.11.001
dc.rights.licenseCC-BY-NC-ND
dc.date.updated2022-03-26T13:36:46Z
refterms.dateFOA2022-03-30T10:20:14Z
dc.openaccess.statusopenAccess
dc.date.accepted2021-11-04


Item file(s)

Thumbnail
Name:
zhao_et_al_2022.pdf
Size:
2.639Mb
Format:
PDF
Thumbnail
Name:
Generaldiscriminativeoptimizat ...
Size:
1.737Mb
Format:
PDF
Description:
Keep supressed - version of record

This item appears in the following Collection(s)

Show simple item record