Procrustean Normal Distribution for Non-Rigid Structure from Motion
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Minsik | - |
dc.contributor.author | Cho, Jungchan | - |
dc.contributor.author | Oh, Songhwai | - |
dc.date.accessioned | 2021-06-22T14:01:45Z | - |
dc.date.available | 2021-06-22T14:01:45Z | - |
dc.date.created | 2021-01-21 | - |
dc.date.issued | 2017-07 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/9478 | - |
dc.description.abstract | A well-defined deformation model can be vital for non-rigid structure from motion (NRSfM). Most existing methods restrict the deformation space by assuming a fixed rank or smooth deformation, which are not exactly true in the real world, and they require the degree of deformation to be predetermined, which is impractical. Meanwhile, the errors in rotation estimation can have severe effects on the performance, i.e., these errors can make a rigid motion be misinterpreted as a deformation. In this paper, we propose an alternative to resolve these issues, motivated by an observation that non-rigid deformations, excluding rigid changes, can be concisely represented in a linear subspace without imposing any strong constraints, such as smoothness or low-rank. This observation is embedded in our new prior distribution, the Procrustean normal distribution (PND), which is a shape distribution exclusively for non-rigid deformations. Because of this unique characteristic of the PND, rigid and non-rigid changes can be strictly separated, which leads to better performance. The proposed algorithm, EM-PND, fits a PND to given 2D observations to solve NRSfM without any user-determined parameters. The experimental results show that EM-PND gives the state-of-the-art performance for the benchmark data sets, confirming the adequacy of the new deformation model. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Procrustean Normal Distribution for Non-Rigid Structure from Motion | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Minsik | - |
dc.identifier.doi | 10.1109/TPAMI.2016.2596720 | - |
dc.identifier.scopusid | 2-s2.0-85020443144 | - |
dc.identifier.wosid | 000402744400009 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.39, no.7, pp.1388 - 1400 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.citation.title | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.citation.volume | 39 | - |
dc.citation.number | 7 | - |
dc.citation.startPage | 1388 | - |
dc.citation.endPage | 1400 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | SHAPE | - |
dc.subject.keywordPlus | RECOVERY | - |
dc.subject.keywordPlus | MODELS | - |
dc.subject.keywordAuthor | Procrustean normal distribution | - |
dc.subject.keywordAuthor | non-rigid structure from motion | - |
dc.subject.keywordAuthor | structure from motion | - |
dc.subject.keywordAuthor | statistical shape model | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/7527684/ | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.