Robust temporal super-resolution for dynamic motion videos
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Bumjun | - |
dc.contributor.author | Yu, Songhyun | - |
dc.contributor.author | Jeong, Jechang | - |
dc.date.accessioned | 2021-07-30T05:22:56Z | - |
dc.date.available | 2021-07-30T05:22:56Z | - |
dc.date.created | 2021-05-13 | - |
dc.date.issued | 2019-10 | - |
dc.identifier.issn | 2473-9936 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/4520 | - |
dc.description.abstract | It is difficult to apply most video temporal super-resolution studies for real-world scenes because they are optimized for a specific range of characteristics. In this paper, we propose a video temporal super-resolution method that is tolerant to motion diversity and noise. Our proposed method improves its robustness by fine-tuning the pre-trained SPyNet that is trained for videos with simple motions and moderate conditions. Moreover, our proposed network learns to accurately synthesize two frames generated by a backward warping function without requiring any additional information using the architecture of a modified DHDN. This enables our proposed method to efficiently synthesize two warped frames by saving the computational complexity for pre-training and extracting the additional information. Finally, we apply the self-ensemble method, which is commonly used in studies on image processing but not on video processing. The application of the self-ensemble method enables our network to generate stable output frames with improved quality without any additional training. Our proposed network proved its performance by ranking 5th in the AIM 2019 video temporal super-resolution challenge; the performance gap between our proposed network and the 3rd- and 4th-ranked solutions was very small. The source code and pre-trained models are available at https://github.com/BumjunPark/DVTSR. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Robust temporal super-resolution for dynamic motion videos | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Jeong, Jechang | - |
dc.identifier.doi | 10.1109/ICCVW.2019.00433 | - |
dc.identifier.scopusid | 2-s2.0-85082474635 | - |
dc.identifier.wosid | 000554591603083 | - |
dc.identifier.bibliographicCitation | Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019, pp.3494 - 3502 | - |
dc.relation.isPartOf | Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 | - |
dc.citation.title | Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 | - |
dc.citation.startPage | 3494 | - |
dc.citation.endPage | 3502 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Imaging Science & Photographic Technology | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Imaging Science & Photographic Technology | - |
dc.subject.keywordPlus | Computer vision | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Optical resolving power | - |
dc.subject.keywordPlus | Dynamic motions | - |
dc.subject.keywordPlus | Ensemble methods | - |
dc.subject.keywordPlus | Frame interpolation | - |
dc.subject.keywordPlus | Performance gaps | - |
dc.subject.keywordPlus | Pre-training | - |
dc.subject.keywordPlus | Temporal super resolution | - |
dc.subject.keywordPlus | Video processing | - |
dc.subject.keywordPlus | Warping function | - |
dc.subject.keywordPlus | Video signal processing | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Frame interpolation | - |
dc.subject.keywordAuthor | Temporal super resolution | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9022289 | - |
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.