Face2Face is a novel approach for real-time facial reenactment of a monocular target video sequence such as a Youtube video in real-time. The source sequence is also a monocular video stream, captured live with a commodity webcam. They can animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. At run time, they track facial expressions of both source and target video, and then the reenactment is achieved by an efficient deformation between source and target. Finally, they re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination. They demonstrated their method in a live setup, where Youtube videos are reenacted in real time.
No comments:
Post a Comment