FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

Yuval Nirkin, Yosi Keller, Tal Hassner

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

We present Face Swapping GAN (FSGAN) for face swapping and reenactment. Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training on those faces. We derive a novel iterative deep learning-based approach for face reenactment which adjusts significant pose and expression variations that can be applied to a single image or a video sequence. For video sequences, we introduce a continuous interpolation of the face views based on reenactment, Delaunay Triangulation, and barycentric coordinates. Occluded face regions are handled by a face completion network. Finally, we use a face blending network for seamless blending of the two faces while preserving the target skin color and lighting conditions. This network uses a novel Poisson blending loss combining Poisson optimization with a perceptual loss. We compare our approach to existing state-of-the-art systems and show our results to be both qualitatively and quantitatively superior. This work describes extensions of the FSGAN method, proposed in an earlier conference version of our work (Nirkin et al. 2019), as well as additional experiments and results.

Original languageEnglish
Pages (from-to)560-575
Number of pages16
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume45
Issue number1
DOIs
StatePublished - 1 Jan 2023

Bibliographical note

Publisher Copyright:
© 1979-2012 IEEE.

Keywords

  • Face swapping
  • deep learning
  • face reenactment

Fingerprint

Dive into the research topics of 'FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment'. Together they form a unique fingerprint.

Cite this