RSGAN: Face swapping and editing using face and hair representation in latent spaces

Ryota Natsume, Tatsuya Yatagawa, Shigeo Morishima

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

This abstract introduces a generative neural network for face swapping and editing face images. We refer to this network as "region-separative generative adversarial network (RSGAN)". In existing deep generative models such as Variational autoencoder (VAE) and Generative adversarial network (GAN), training data must represent what the generative models synthesize. For example, image inpainting is achieved by training images with and without holes. However, it is difficult or even impossible to prepare a dataset which includes face images both before and after face swapping because faces of real people cannot be swapped without surgical operations. We tackle this problem by training the network so that it synthesizes synthesize a natural face image from an arbitrary pair of face and hair appearances. In addition to face swapping, the proposed network can be applied to other editing applications, such as visual attribute editing and random face parts synthesis.

Original languageEnglish
Title of host publicationACM SIGGRAPH 2018 Posters, SIGGRAPH 2018
PublisherAssociation for Computing Machinery, Inc
ISBN (Print)9781450358170
DOIs
Publication statusPublished - 2018 Aug 12
EventACM SIGGRAPH 2018 Posters - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2018 - Vancouver, Canada
Duration: 2018 Aug 122018 Aug 16

Publication series

NameACM SIGGRAPH 2018 Posters, SIGGRAPH 2018

Other

OtherACM SIGGRAPH 2018 Posters - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2018
Country/TerritoryCanada
CityVancouver
Period18/8/1218/8/16

Keywords

  • Face
  • Face swapping
  • Image editing
  • Portrait

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'RSGAN: Face swapping and editing using face and hair representation in latent spaces'. Together they form a unique fingerprint.

Cite this