Using Fully Connected and Convolutional Net for GAN-Based Face Swapping

Bo Shue Lin, Ding Wen Hsu, Chin Han Shen, Hsu Feng Hsiao

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

Abstract

The lifelike results of using face swapping have contributed greatly to the research in computer vision. In this work, we extend the architecture of faceswap-GAN in order to obtain more natural results compared to the original framework. In the original architecture, the self-attention module usually converts the facial features from a source face to the target face with artificial distortion around the facial features. We use a structure of fully connected convolutional layers as a discriminator to approach the problem. The outcome can be smoother and more natural perceptually compared to the results using the original faceswap-GAN.

Original languageEnglish
Title of host publicationProceedings of 2020 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2020
EditorsXuan-Tu Tran, Duy-Hieu Bui
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages185-188
Number of pages4
ISBN (Electronic)9781728193960
DOIs
StatePublished - 8 Dec 2020
Event16th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2020 - Virtual, Halong, Viet Nam
Duration: 8 Dec 202010 Dec 2020

Publication series

NameProceedings of 2020 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2020

Conference

Conference16th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2020
CountryViet Nam
CityVirtual, Halong
Period8/12/2010/12/20

Keywords

  • Deepfake
  • fully-connected and convolutional network
  • Generative adversarial network (GAN)

Fingerprint Dive into the research topics of 'Using Fully Connected and Convolutional Net for GAN-Based Face Swapping'. Together they form a unique fingerprint.

Cite this