网络文章整理
PART 1
http://disinfo.com/2016/03/face2face-real-time-face-capture-and-reenactment-of-rgb-videos/
Face2Face: Real-time Face Capture and Reenactment
Today, we can kiss reality goodbye. Stanford, University of Erlangen-Nuremberg and Max Planck Institute for Informatics unveiled their latest project and it is very scary. They have developed a technology that can manipulate youtube videos in real-time with a basic web camera. The implications of these technology are very serious.
Abstract:
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.
Now that scene from Bruce Almighty is actually possible…
- About
- Latest Posts
Harry Henderson
PART 2
Face2Face: Real-time Face Capture and Reenactment of RGB Videos
Proc. Computer Vision and Pattern Recognition (CVPR), IEEE, June 2016 Abstract
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.
Extras
Paper: 
PDF
Supplemental Materials: 
ZIP
BibTeX: 
.bib
Google Scholar: 
