Japanese kanji font style transfer based on GAN with unpaired training

Hiroki Sakai, Daisuke Niino, Takashi Ijiri

研究成果: Conference contribution

抄録

To design a whole package of Japanese font is labor consuming, since it usually contains about 30k kanji characters. To support an efficient design process, this poster attempts to adopt a style transfer algorithm for font package completion. Given two font packages where one contains all characters and the other lacks a large part, we train CycleGAN to perform style transfer between the two packages and transfer the style from the former to the latter. To illustrate the feasibility of our technique, we performed style transfer experiments and achieved visually plausible results by using a relatively small training data set.

本文言語English
ホスト出版物のタイトルPacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings
編集者Hongbo Fu, Abhijeet Ghosh, Johannes Kopf
出版社IEEE Computer Society
ページ5-6
ページ数2
ISBN(電子版)9783038680734
DOI
出版ステータスPublished - 2018
イベント26th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 2018 - Hong Kong, Hong Kong
継続期間: 2018 10月 82018 10月 11

出版物シリーズ

名前Proceedings - Pacific Conference on Computer Graphics and Applications
2018-October
ISSN(印刷版)1550-4085

Conference

Conference26th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 2018
国/地域Hong Kong
CityHong Kong
Period18/10/818/10/11

ASJC Scopus subject areas

  • ソフトウェア
  • 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
  • モデリングとシミュレーション

フィンガープリント

「Japanese kanji font style transfer based on GAN with unpaired training」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