Generation and Extraction of Color Palettes with Adversarial Variational Auto-Encoders

Ahmad Moussa*, Hiroshi Watanabe

*この研究の対応する著者

研究成果: Conference contribution

抄録

The process of creating a meaningful and perceptually pleasing color palette is an incredibly difficult task for the inexperienced practitioner. In this paper we show that the Variational Auto Encoder can be a powerful creative tool for the generation of novel color palettes as well as their extraction from visual mediums. Our proposed model is capable of extracting meaningful color palettes from images, and simultaneously learns an internal representation which allows for the sampling of novel color palettes without any additional input.

本文言語English
ホスト出版物のタイトルProceedings of 6th International Congress on Information and Communication Technology, ICICT 2021
編集者Xin-She Yang, Simon Sherratt, Nilanjan Dey, Amit Joshi
出版社Springer Science and Business Media Deutschland GmbH
ページ889-897
ページ数9
ISBN(印刷版)9789811623790
DOI
出版ステータスPublished - 2022
イベント6th International Congress on Information and Communication Technology, ICICT 2021 - Virtual, Online
継続期間: 2021 2 252021 2 26

出版物シリーズ

名前Lecture Notes in Networks and Systems
236
ISSN(印刷版)2367-3370
ISSN(電子版)2367-3389

Conference

Conference6th International Congress on Information and Communication Technology, ICICT 2021
CityVirtual, Online
Period21/2/2521/2/26

ASJC Scopus subject areas

  • 制御およびシステム工学
  • 信号処理
  • コンピュータ ネットワークおよび通信

フィンガープリント

「Generation and Extraction of Color Palettes with Adversarial Variational Auto-Encoders」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