Learning photo enhancement by black-box model optimization data generation

Mayu Omiya, Edgar Simo Serra, Satoshi Iizuka, Hiroshi Ishikawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We address the problem of automatic photo enhancement, in which the challenge is to determine the optimal enhancement for a given photo according to its content. For this purpose, we train a convolutional neural network to predict the best enhancement for given picture. While such machine learning techniques have shown great promise in photo enhancement, there are some limitations. One is the problem of interpretability, i.e., that it is not easy for the user to discern what has been done by a machine. In this work, we leverage existing manual photo enhancement tools as a black-box model, and predict the enhancement parameters of that model. Because the tools are designed for human use, the resulting parameters can be interpreted by their users. Another problem is the difficulty of obtaining training data.We propose generating supervised training data from high-quality professional images by randomly sampling realistic de-enhancement parameters. We show that this approach allows automatic enhancement of photographs without the need for large manually labelled supervised training datasets.

Original languageEnglish
Title of host publicationSIGGRAPH Asia 2018 Technical Briefs, SA 2018
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450360623
DOIs
Publication statusPublished - 2018 Dec 4
EventSIGGRAPH Asia 2018 Technical Briefs - International Conference on Computer Graphics and Interactive Techniques, SA 2018 - Tokyo, Japan
Duration: 2018 Dec 42018 Dec 7

Other

OtherSIGGRAPH Asia 2018 Technical Briefs - International Conference on Computer Graphics and Interactive Techniques, SA 2018
CountryJapan
CityTokyo
Period18/12/418/12/7

Keywords

  • Black-box optimization
  • Machine learning
  • Photo enhancement

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Learning photo enhancement by black-box model optimization data generation'. Together they form a unique fingerprint.

  • Cite this

    Omiya, M., Simo Serra, E., Iizuka, S., & Ishikawa, H. (2018). Learning photo enhancement by black-box model optimization data generation. In SIGGRAPH Asia 2018 Technical Briefs, SA 2018 [a7] Association for Computing Machinery, Inc. https://doi.org/10.1145/3283254.3283286