Fast style transfer for Chinese tranditional ink painting

Renjie Zhou, Jeong Hoon Han, Hyeon Seok Yang, Woojin Jeong, Young Shik Moon

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

7 Scopus citations

Abstract

By style transfer mechanism, the style of another image can be illustrated toward another target picture. However, calculating speed and quality are two tricky issues. In this paper, we propose an accelerated version of the transfer for Chinese traditional ink painting style. By reducing the size of the rendering network, the training speed can be increased to 1.27 times. It is about the similar quality as the image generated by the original model. This can also reflect the characteristics of ink painting: Light ink, black and white.

Original languageEnglish
Title of host publicationICEIEC 2019 - Proceedings of 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication
EditorsWenzheng Li, Guomin Zuo
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages586-588
Number of pages3
ISBN (Electronic)9781728111896
DOIs
StatePublished - Jul 2019
Event9th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2019 - Beijing, China
Duration: 12 Jul 201914 Jul 2019

Publication series

NameICEIEC 2019 - Proceedings of 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication

Conference

Conference9th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2019
Country/TerritoryChina
CityBeijing
Period12/07/1914/07/19

Keywords

  • Chinese Traditional Painting
  • Deep Learning
  • Style Transfer

Cite this