Unsupervised Image-to-Image Translation Based on Bidirectional Style Transfer

  • Hyunkyu Park
  • , Sungho Kang
  • , Yeong Hyeon Park
  • , Yeonho Lee
  • , Hanbyul Lee
  • , Seho Bae
  • , Juneho Yi

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

Abstract

Image-to-image translation (I2I) is an image synthesis technique to map a source image to the style of the target domain while preserving its content information. Existing image-to-image translation study results showed excellent image synthesis performance using generative adversarial network (GAN) based models, but they are not capable of efficiently handling the style of the target domain. To overcome this limitation, a bidirectional style transfer network has been developed to perform image synthesis by intersecting images of two domains with each other's styles, but the type of applicable dataset is limited due to supervised learning-based training. We proposed an unsupervised image-to-image translation method by employing a bidirectional style transfer network with a cyclic collaborative loss to train the model. Experimental results showed that the proposed network accurately reflected the style of the target domain in the image synthesis task.

Original languageEnglish
Title of host publicationProceedings of the 2023 IEEE 6th International Conference on Knowledge Innovation and Invention, ICKII 2023
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages671-676
Number of pages6
ISBN (Electronic)9798350323535
DOIs
StatePublished - 2023
Event6th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2023 - Sapporo, Japan
Duration: 11 Aug 202313 Aug 2023

Publication series

NameProceedings of the 2023 IEEE 6th International Conference on Knowledge Innovation and Invention, ICKII 2023

Conference

Conference6th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2023
Country/TerritoryJapan
CitySapporo
Period11/08/2313/08/23

Keywords

  • bidirectional network
  • style transfer
  • unsupervised image-to-image translation (I2I)

Fingerprint

Dive into the research topics of 'Unsupervised Image-to-Image Translation Based on Bidirectional Style Transfer'. Together they form a unique fingerprint.

Cite this