Single Image Deraining Using Time-Lapse Data
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Jaehoon | - |
dc.contributor.author | Kim, Seungryong | - |
dc.contributor.author | Min, Dongbo | - |
dc.contributor.author | Sohn, Kwanghoon | - |
dc.date.accessioned | 2021-08-31T15:57:12Z | - |
dc.date.available | 2021-08-31T15:57:12Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2020 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/58923 | - |
dc.description.abstract | Leveraging on recent advances in deep convolutional neural networks (CNNs), single image deraining has been studied as a learning task, achieving an outstanding performance over traditional hand-designed approaches. Current CNNs based deraining approaches adopt the supervised learning framework that uses a massive training data generated with synthetic rain streaks, having a limited generalization ability on real rainy images. To address this problem, we propose a novel learning framework for single image deraining that leverages time-lapse sequences instead of the synthetic image pairs. The deraining networks are trained using the time-lapse sequences in which both camera and scenes are static except for time-varying rain streaks. Specifically, we formulate a background consistency loss such that the deraining networks consistently generate the same derained images from the time-lapse sequences. We additionally introduce two loss functions, the structure similarity loss that encourages the derained image to be similar with an input rainy image and the directional gradient loss using the assumption that the estimated rain streaks are likely to be sparse and have dominant directions. To consider various rain conditions, we leverage a dynamic fusion module that effectively fuses multi-scale features. We also build a novel large-scale time-lapse dataset providing real world rainy images containing various rain conditions. Experiments demonstrate that the proposed method outperforms state-of-the-art techniques on synthetic and real rainy images both qualitatively and quantitatively. On the high-level vision tasks under severe rainy conditions, it has been shown that the proposed method can be utilized as a pre-preprocessing step for subsequent tasks. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | REMOVAL | - |
dc.title | Single Image Deraining Using Time-Lapse Data | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Seungryong | - |
dc.identifier.doi | 10.1109/TIP.2020.3000612 | - |
dc.identifier.wosid | 000553851400003 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON IMAGE PROCESSING, v.29, pp.7274 - 7289 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON IMAGE PROCESSING | - |
dc.citation.title | IEEE TRANSACTIONS ON IMAGE PROCESSING | - |
dc.citation.volume | 29 | - |
dc.citation.startPage | 7274 | - |
dc.citation.endPage | 7289 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
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 | REMOVAL | - |
dc.subject.keywordAuthor | Rain | - |
dc.subject.keywordAuthor | Training data | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | Rendering (computer graphics) | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Single image deraining | - |
dc.subject.keywordAuthor | convolutional neural networks (CNNs) | - |
dc.subject.keywordAuthor | time-lapse dataset | - |
dc.subject.keywordAuthor | dynamic fusion module | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea 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.