Procrustean Regression Networks: Learning 3D Structure of Non-rigid Objects from 2D Annotations
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Sungheon | - |
dc.contributor.author | Lee, Minsik | - |
dc.contributor.author | Kwak, Nojun | - |
dc.date.accessioned | 2021-06-22T09:11:01Z | - |
dc.date.available | 2021-06-22T09:11:01Z | - |
dc.date.issued | 2020-08 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/1512 | - |
dc.description.abstract | We propose a novel framework for training neural networks which is capable of learning 3D information of non-rigid objects when only 2D annotations are available as ground truths. Recently, there have been some approaches that incorporate the problem setting of non-rigid structure-from-motion (NRSfM) into deep learning to learn 3D structure reconstruction. The most important difficulty of NRSfM is to estimate both the rotation and deformation at the same time, and previous works handle this by regressing both of them. In this paper, we resolve this difficulty by proposing a loss function wherein the suitable rotation is automatically determined. Trained with the cost function consisting of the reprojection error and the low-rank term of aligned shapes, the network learns the 3D structures of such objects as human skeletons and faces during the training, whereas the testing is done in a single-frame basis. The proposed method can handle inputs with missing entries and experimental results validate that the proposed framework shows superior reconstruction performance to the state-of-the-art method on the Human 3.6M, 300-VW, and SURREAL datasets, even though the underlying network structure is very simple. © 2020, Springer Nature Switzerland AG. | - |
dc.format.extent | 18 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Springer Science and Business Media Deutschland GmbH | - |
dc.title | Procrustean Regression Networks: Learning 3D Structure of Non-rigid Objects from 2D Annotations | - |
dc.type | Article | - |
dc.publisher.location | 독일 | - |
dc.identifier.doi | 10.1007/978-3-030-58526-6_1 | - |
dc.identifier.scopusid | 2-s2.0-85093115970 | - |
dc.identifier.bibliographicCitation | Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX, pp 1 - 18 | - |
dc.citation.title | Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 18 | - |
dc.type.docType | Conference Paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Computer vision | - |
dc.subject.keywordPlus | Cost functions | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Object recognition | - |
dc.subject.keywordPlus | 3D information | - |
dc.subject.keywordPlus | Learning to learn | - |
dc.subject.keywordPlus | Loss functions | - |
dc.subject.keywordPlus | Non-rigid objects | - |
dc.subject.keywordPlus | Reprojection error | - |
dc.subject.keywordPlus | State-of-the-art methods | - |
dc.subject.keywordPlus | Structure from motion | - |
dc.subject.keywordPlus | Underlying networks | - |
dc.subject.keywordPlus | Rigid structures | - |
dc.identifier.url | https://link.springer.com/chapter/10.1007/978-3-030-58526-6_1 | - |
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.