Supervised and unsupervised learning of parameterized color enhancement

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

20 Scopus citations

Abstract

We treat the problem of color enhancement as an image translation task, which we tackle using both supervised and unsupervised learning. Unlike traditional image to image generators, our translation is performed using a global parameterized color transformation instead of learning to directly map image information. In the supervised case, every training image is paired with a desired target image and a convolutional neural network (CNN) learns from the expert retouched images the parameters of the transformation. In the unpaired case, we employ two-way generative adversarial networks (GANs) to learn these parameters and apply a circularity constraint. We achieve state-of-the-art results compared to both supervised (paired data) and unsupervised (unpaired data) image enhancement methods on the MIT-Adobe FiveK benchmark. Moreover, we show the generalization capability of our method, by applying it on photos from the early 20th century and to dark video frames.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages981-989
Number of pages9
ISBN (Electronic)9781728165530
DOIs
StatePublished - Mar 2020
Event2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
Duration: 1 Mar 20205 Mar 2020

Publication series

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Country/TerritoryUnited States
CitySnowmass Village
Period1/03/205/03/20

Funding

FundersFunder number
ERC-StG
European Unions Horizon 2020 research and innovation programERC CoG 725974
Horizon 2020 Framework Programme757497, 725974
European Commission

    Fingerprint

    Dive into the research topics of 'Supervised and unsupervised learning of parameterized color enhancement'. Together they form a unique fingerprint.

    Cite this