Photo-realistic image dehazing and verifying networks via complementary adversarial learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, J. | - |
dc.contributor.author | Paik, Joonki | - |
dc.date.accessioned | 2021-09-27T03:40:09Z | - |
dc.date.available | 2021-09-27T03:40:09Z | - |
dc.date.issued | 2021-09 | - |
dc.identifier.issn | 1424-8220 | - |
dc.identifier.issn | 1424-3210 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/49912 | - |
dc.description.abstract | Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze model estimation process requires very high computational complexity. To solve this problem by directly estimating the radiance of the haze images, we present a novel dehazing and verifying network (DVNet). In the dehazing procedure, we enhanced the clean images by using a correction network (CNet), which uses the ground truth to learn the haze network. Haze images are then restored through a haze network (HNet). Furthermore, a verifying method verifies the error of both CNet and HNet using a self-supervised learning method. Finally, the proposed complementary adversarial learning method can produce results more naturally. Note that the proposed discriminator and generators (HNet & CNet) can be learned via an unpaired dataset. Overall, the proposed DVNet can generate a better dehazed result than state-of-the-art approaches under various hazy conditions. Experimental results show that the DVNet outperforms state-of-the-art dehazing methods in most cases. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | MDPI | - |
dc.title | Photo-realistic image dehazing and verifying networks via complementary adversarial learning | - |
dc.type | Article | - |
dc.identifier.doi | 10.3390/s21186182 | - |
dc.identifier.bibliographicCitation | Sensors, v.21, no.18 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000701206800001 | - |
dc.identifier.scopusid | 2-s2.0-85114881035 | - |
dc.citation.number | 18 | - |
dc.citation.title | Sensors | - |
dc.citation.volume | 21 | - |
dc.type.docType | Article | - |
dc.publisher.location | 스위스 | - |
dc.subject.keywordAuthor | CNN | - |
dc.subject.keywordAuthor | Dehazing | - |
dc.subject.keywordAuthor | GAN | - |
dc.subject.keywordPlus | Demulsification | - |
dc.subject.keywordPlus | Image enhancement | - |
dc.subject.keywordPlus | Light transmission | - |
dc.subject.keywordPlus | Lighting | - |
dc.subject.keywordPlus | Adversarial learning | - |
dc.subject.keywordPlus | Environmental variables | - |
dc.subject.keywordPlus | Model estimation | - |
dc.subject.keywordPlus | Photorealistic images | - |
dc.subject.keywordPlus | Physical model | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | State-of-the-art approach | - |
dc.subject.keywordPlus | Supervised learning methods | - |
dc.subject.keywordPlus | Learning systems | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Instruments & Instrumentation | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Analytical | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Instruments & Instrumentation | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang 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.