Face2Face: Real-time Face Capture and Reenactment of RGB Videos

2016

Conference Paper

ncs

We present a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. To this end, we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling. At run time, we track facial expressions of both source and target video using a dense photometric consistency measure. Reenactment is then achieved by fast and efficient deformation transfer between source and target. The mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit. Finally, we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination. We demonstrate our method in a live setup, where Youtube videos are reenacted in real time.

@inproceedings{thies2016face,
  title = {Face2Face: Real-time Face Capture and Reenactment of RGB Videos},
  author = {Thies, J. and Zollh{\"o}fer, M. and Stamminger, M. and Theobalt, C. and Nie{\ss}ner, M.},
  booktitle = {Proc. Computer Vision and Pattern Recognition (CVPR), IEEE},
  year = {2016},
  doi = {},
  url = {https://justusthies.github.io/posts/face2face/}
}