Real-time face capture and reenactment of videos
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.
The development, which is as equally impressive as it is disturbing, is the result of a collaboration between researchers from Germany’s University of Erlangen-Nuremberg, the Max-Planck Institute for Informatics, and Stanford University in California.
The study, Face2Face: Real-time Face Capture and Reenactment of RGB Videos,
“animates the facial expressions of the target video by a source actor and re-renders the manipulated output video in a photo-realistic fashion,” according to the researchers.
thanks to xxx for the link..
now this is sort of scary and disturbing..just think of the possibilities..and this can also be done retrospectively on old video and footage as we can see from the examples in the video..the mind boggles at what could be achieved..and if we are finding out about it now..how long has it been a tool of the controllers?