On the Duality Between Retinex and Image Dehazing

Simple item page
dc.contributor.authorGaldran, Adrian
dc.contributor.authorBria, Alessandro
dc.contributor.authorAlvarez-Gila, Aitor
dc.contributor.authorVazquez-Corral, Javier
dc.contributor.authorBertalmío, Marcelo
dc.contributor.institutionTecnalia Research & Innovation
dc.contributor.institutionVISUAL
dc.date.issued2018-12-14
dc.descriptionPublisher Copyright: © 2018 IEEE.
dc.description.abstractImage dehazing deals with the removal of undesired loss of visibility in outdoor images due to the presence of fog. Retinex is a color vision model mimicking the ability of the Human Visual System to robustly discount varying illuminations when observing a scene under different spectral lighting conditions. Retinex has been widely explored in the computer vision literature for image enhancement and other related tasks. While these two problems are apparently unrelated, the goal of this work is to show that they can be connected by a simple linear relationship. Specifically, most Retinex-based algorithms have the characteristic feature of always increasing image brightness, which turns them into ideal candidates for effective image dehazing by directly applying Retinex to a hazy image whose intensities have been inverted. In this paper, we give theoretical proof that Retinex on inverted intensities is a solution to the image dehazing problem. Comprehensive qualitative and quantitative results indicate that several classical and modern implementations of Retinex can be transformed into competing image dehazing algorithms performing on pair with more complex fog removal methods, and can overcome some of the main challenges associated with this problem.en
dc.description.statusPeer reviewed
dc.format.extent10
dc.format.extent1858950
dc.identifier.citationGaldran , A , Bria , A , Alvarez-Gila , A , Vazquez-Corral , J & Bertalmío , M 2018 , On the Duality Between Retinex and Image Dehazing . in unknown . 1063-6919 , IEEE Computer Society , pp. 8212-8221 , 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 , Salt Lake City , United States , 18/06/18 . https://doi.org/10.1109/CVPR.2018.00857
dc.identifier.citationconference
dc.identifier.doi10.1109/CVPR.2018.00857
dc.identifier.isbn978-1-5386-6420-9
dc.identifier.isbn9781538664209
dc.identifier.otherresearchoutputwizard: 11556/694
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85061789666&partnerID=8YFLogxK
dc.language.isoeng
dc.publisherIEEE Computer Society
dc.relation.ispartofunknown
dc.relation.ispartofseries1063-6919
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsRetinex
dc.subject.keywordsDehazing
dc.subject.keywordsImage processing
dc.subject.keywordsRetinex
dc.subject.keywordsDehazing
dc.subject.keywordsImage processing
dc.subject.keywordsSoftware
dc.subject.keywordsComputer Vision and Pattern Recognition
dc.titleOn the Duality Between Retinex and Image Dehazingen
dc.typeconference output
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Galdran_On_the_Duality_CVPR_2018_paper.pdf
Size:
1.77 MB
Format:
Adobe Portable Document Format
Description:
Open access version of the paper, accessible from http://openaccess.thecvf.com/content_cvpr_2018/html/Galdran_On_the_Duality_CVPR_2018_paper.html
Download