Universal Framework for Joint Image Restoration and 3D Body Reconstruction
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lumentut, Jonathan Samuel | - |
dc.contributor.author | Marchellus, Matthew | - |
dc.contributor.author | Santoso, Joshua | - |
dc.contributor.author | Kim, Tae Hyun | - |
dc.contributor.author | Chang, Ju Yong | - |
dc.contributor.author | Park, In Kyu | - |
dc.date.accessioned | 2022-07-06T02:22:26Z | - |
dc.date.available | 2022-07-06T02:22:26Z | - |
dc.date.created | 2022-01-05 | - |
dc.date.issued | 2021-12 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/138597 | - |
dc.description.abstract | Recent works have demonstrated excellent state-of-the-art achievements in image restoration and 3D body reconstruction from an input image. The 3D body reconstruction task, however, relies heavily on the input image's quality. A straightforward way to solve this issue is by generating vast degraded datasets and using them in a re-finetuned or newly-crafted body reconstruction network. However, in future usage, these datasets may become obsolete, leaving the newly-crafted network outdated. Unlike this approach, we design a universal framework that is able to utilize prior state-of-the-art restoration works and then self-boosts their performances during test-time while jointly carrying out the 3D body reconstruction. The self-boosting mechanism is adopted via test-time parameter adaptation capable of handling various types of degradation. To accommodate, we also propose a strategy that generates pseudo-data on the fly during test-time, allowing both restoration and reconstruction modules to be learned in a self-supervised manner. With this advantage, the universal framework intelligently enhances the performance without any new dataset or new neural network model involvement. Our experimental results show that using the proposed framework and pseudo-data strategies significantly improves the performances of both scenarios. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Universal Framework for Joint Image Restoration and 3D Body Reconstruction | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Tae Hyun | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3132148 | - |
dc.identifier.scopusid | 2-s2.0-85120538400 | - |
dc.identifier.wosid | 000730528400001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.9, pp.162543 - 162552 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 9 | - |
dc.citation.startPage | 162543 | - |
dc.citation.endPage | 162552 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordPlus | Restoration | - |
dc.subject.keywordPlus | 3d body reconstruction | - |
dc.subject.keywordPlus | Body reconstruction | - |
dc.subject.keywordPlus | De-noising | - |
dc.subject.keywordPlus | Deblur | - |
dc.subject.keywordPlus | Metalearning | - |
dc.subject.keywordPlus | Performance | - |
dc.subject.keywordPlus | Pseudo-data | - |
dc.subject.keywordPlus | Self-adaptive | - |
dc.subject.keywordPlus | Superresolution | - |
dc.subject.keywordPlus | Test time | - |
dc.subject.keywordPlus | Image reconstruction | - |
dc.subject.keywordAuthor | Image reconstruction | - |
dc.subject.keywordAuthor | Three-dimensional displays | - |
dc.subject.keywordAuthor | Image restoration | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Noise reduction | - |
dc.subject.keywordAuthor | Noise measurement | - |
dc.subject.keywordAuthor | Restoration | - |
dc.subject.keywordAuthor | deblur | - |
dc.subject.keywordAuthor | super-resolution | - |
dc.subject.keywordAuthor | denoising | - |
dc.subject.keywordAuthor | 3D body reconstruction | - |
dc.subject.keywordAuthor | meta-learning | - |
dc.subject.keywordAuthor | self-adaptive | - |
dc.subject.keywordAuthor | pseudo-data | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.