Learning photo enhancement by black-box model optimization data generation

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

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルSIGGRAPH Asia 2018 Technical Briefs, SA 2018
出版社Association for Computing Machinery, Inc
ISBN(電子版)9781450360623
DOI
出版ステータスPublished - 2018 12 4
イベントSIGGRAPH Asia 2018 Technical Briefs - International Conference on Computer Graphics and Interactive Techniques, SA 2018 - Tokyo, Japan
継続期間: 2018 12 42018 12 7

Other

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

ASJC Scopus subject areas

  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • コンピュータ ビジョンおよびパターン認識
  • 人間とコンピュータの相互作用
  • ソフトウェア

フィンガープリント

「Learning photo enhancement by black-box model optimization data generation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル