Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Deep Illumination-Aware Dehazing With Low-Light and Detail Enhancement

Full metadata record
DC Field Value Language
dc.contributor.authorKim, G.-
dc.contributor.authorKwon, Junseok-
dc.date.accessioned2021-10-29T00:40:10Z-
dc.date.available2021-10-29T00:40:10Z-
dc.date.issued2022-03-
dc.identifier.issn1524-9050-
dc.identifier.issn1558-0016-
dc.identifier.urihttps://scholarworks.bwise.kr/cau/handle/2019.sw.cau/50875-
dc.description.abstractWe present a novel dehazing framework for real-world images that contain both hazy and low-light areas. Dehazing and low-light enhancements are unified by using an illumination map that is estimated using a proposed convolutional neural network. The illumination map is then used as a component for three different tasks: atmospheric light estimation, transmission map estimation, and low-light enhancement, thereby enabling the solving of interrelated low-level vision problems simultaneously. To train the neural network to perform both dehazing and low-light enhancement, we synthesize hazy and low-light images from normal images. Experimental results demonstrate that the proposed method quantitatively and qualitatively outperforms state-of-the-art algorithms in real-world image dehazing. IEEE-
dc.format.extent15-
dc.language영어-
dc.language.isoENG-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.titleDeep Illumination-Aware Dehazing With Low-Light and Detail Enhancement-
dc.typeArticle-
dc.identifier.doi10.1109/TITS.2021.3117868-
dc.identifier.bibliographicCitationIEEE Transactions on Intelligent Transportation Systems, v.23, no.3, pp 2494 - 2508-
dc.description.isOpenAccessN-
dc.identifier.wosid000732270200001-
dc.identifier.scopusid2-s2.0-85117322065-
dc.citation.endPage2508-
dc.citation.number3-
dc.citation.startPage2494-
dc.citation.titleIEEE Transactions on Intelligent Transportation Systems-
dc.citation.volume23-
dc.type.docTypeArticle-
dc.publisher.location미국-
dc.subject.keywordAuthorDehazing-
dc.subject.keywordAuthorimage enhancement-
dc.subject.keywordAuthorlow-light enhancement.-
dc.subject.keywordPlusComputer vision-
dc.subject.keywordPlusDemulsification-
dc.subject.keywordPlusLight transmission-
dc.subject.keywordPlusNeural networks-
dc.subject.keywordPlusConvolutional neural network-
dc.subject.keywordPlusDehazing-
dc.subject.keywordPlusDetail enhancement-
dc.subject.keywordPlusLight enhancement-
dc.subject.keywordPlusLight estimations-
dc.subject.keywordPlusLow light-
dc.subject.keywordPlusLow-level vision-
dc.subject.keywordPlusLow-light enhancement.-
dc.subject.keywordPlusMAP estimation-
dc.subject.keywordPlusReal-world image-
dc.subject.keywordPlusImage enhancement-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalResearchAreaTransportation-
dc.relation.journalWebOfScienceCategoryEngineering, Civil-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.relation.journalWebOfScienceCategoryTransportation Science & Technology-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Software > School of Computer Science and Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Kwon, Junseok photo

Kwon, Junseok
소프트웨어대학 (소프트웨어학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE