Deep Recurrent Network for Fast and Full-Resolution Light Field Deblurring
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lumentut, Jonathan Samuel | - |
dc.contributor.author | Kim, Tae Hyun | - |
dc.contributor.author | Ramamoorthi, Ravi | - |
dc.contributor.author | Park, In Kyu | - |
dc.date.accessioned | 2022-07-08T20:28:03Z | - |
dc.date.available | 2022-07-08T20:28:03Z | - |
dc.date.created | 2021-05-12 | - |
dc.date.issued | 2019-12 | - |
dc.identifier.issn | 1070-9908 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/146673 | - |
dc.description.abstract | The popularity of parallax-based image processing is increasing while in contrast early works on recovering sharp light field from its blurry input (deblurring) remain stagnant. State-of-the-art blind light field deblurring methods suffer from several problems such as slow processing, reduced spatial size, and simplified motion blur model. In this paper, we solve these challenging problems by proposing a novel light field recurrent deblurring network that is trained under 6 degree-of-freedom camera motion-blur model. By combining the real light field captured using Lytro Illum and synthetic light field rendering of 3D scenes from UnrealCV, we provide a large-scale blurry light field dataset to train the network. The proposed method outperforms the state-of-the-art methods in terms of deblurring quality, the capability of handling full-resolution, and a fast runtime. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Deep Recurrent Network for Fast and Full-Resolution Light Field Deblurring | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Tae Hyun | - |
dc.identifier.doi | 10.1109/LSP.2019.2947379 | - |
dc.identifier.scopusid | 2-s2.0-85077781128 | - |
dc.identifier.wosid | 000506875000010 | - |
dc.identifier.bibliographicCitation | IEEE SIGNAL PROCESSING LETTERS, v.26, no.12, pp.1788 - 1792 | - |
dc.relation.isPartOf | IEEE SIGNAL PROCESSING LETTERS | - |
dc.citation.title | IEEE SIGNAL PROCESSING LETTERS | - |
dc.citation.volume | 26 | - |
dc.citation.number | 12 | - |
dc.citation.startPage | 1788 | - |
dc.citation.endPage | 1792 | - |
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 | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | Degrees of freedom (mechanics) | - |
dc.subject.keywordPlus | Geometrical optics | - |
dc.subject.keywordPlus | Large dataset | - |
dc.subject.keywordPlus | Recurrent neural networks | - |
dc.subject.keywordPlus | Three dimensional computer graphics | - |
dc.subject.keywordPlus | 6-DOF motion | - |
dc.subject.keywordPlus | Blind deblurring | - |
dc.subject.keywordPlus | dataset | - |
dc.subject.keywordPlus | Light fields | - |
dc.subject.keywordPlus | Recurrent networks | - |
dc.subject.keywordPlus | Image enhancement | - |
dc.subject.keywordAuthor | Recurrent network | - |
dc.subject.keywordAuthor | light field image | - |
dc.subject.keywordAuthor | blind deblurring | - |
dc.subject.keywordAuthor | dataset | - |
dc.subject.keywordAuthor | 6-DOF motion | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/8868185 | - |
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.