본문 바로가기
  • Home

A Multi-domain Style Transfer by Modified Generator of GAN

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2022, 27(7), pp.27-33
  • DOI : 10.9708/jksci.2022.27.07.027
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : May 12, 2022
  • Accepted : July 8, 2022
  • Published : July 29, 2022

Geum-Boon Lee 1

1조선대학교

Accredited

ABSTRACT

In this paper, we propose a novel generator architecture for multi-domain style transfer method not an image to image translation, as a method of generating a styled image by transfering a style to the content image. A latent vector and Gaussian noises are added to the generator of GAN so that a high quality image is generated while considering the characteristics of various data distributions for each domain and preserving the features of the content data. With the generator architecture of the proposed GAN, networks are configured and presented so that the content image can learn the styles for each domain well, and it is applied to the domain composed of images of the four seasons to show the high resolution style transfer results.

Citation status

* References for papers published after 2022 are currently being built.

This paper was written with support from the National Research Foundation of Korea.