Neural Style-Preserving Visual Dubbing

SIGGRAPH Asia 2019

Hyeongwoo Kim1  Mohamed Elgharib1  Michael Zollhöfer2 
Hans-Peter Seidel1  Thabo Beeler3  Christian Richardt4  Christian Theobalt1
1MPI Informatics  2Stanford University 3DisneyResearch|Studios  4University of Bath 

Abstract

Dubbing is a technique for translating video content from one language to another. However, state-of-the-art visual dubbing techniques directly copy facial expressions from source to target actors without considering identity-specific idiosyncrasies such as a unique type of smile. We present a style-preserving visual dubbing approach from single video inputs, which maintains the signature style of target actors when modifying facial expressions, including mouth motions, to match foreign languages. At the heart of our approach is the concept of motion style, in particular for facial expressions, i.e., the person-specific expression change that is yet another essential factor beyond visual accuracy in face editing applications. Our method is based on a recurrent generative adversarial network that captures the spatiotemporal co-activation of facial expressions, and enables generating and modifying the facial expressions of the target actor while preserving their style. We train our model with unsynchronized source and target videos in an unsupervised manner using cycle-consistency and mouth expression losses, and synthesize photorealistic video frames using a layered neural face renderer. Our approach generates temporally coherent results, and handles dynamic backgrounds. Our results show that our dubbing approach maintains the idiosyncratic style of the target actor better than previous approaches, even for widely differing source and target actors.

Links

paper video

Bibtex

@article{kim2019neural,
  title     = {Neural Style-Preserving Visual Dubbing},
  author    = {Kim, Hyeongwoo and Elgharib, Mohamed and Zoll{\"o}fer, Michael 
               Seidel, Hans-Peter and Beeler, Thabo and Richardt, Christian and Theobalt, Christian},
  journal   = {ACM Transactions on Graphics (TOG)},
  volume    = {38},
  number    = {6},
  pages     = {178:1-13},
  year      = {2019}
}