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

From Justus Thies, Michael Zollhöfer, Marc Stamminger, Christian Theobalt and Matthias Nießner:

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... (full paper)

 

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

Novotechnik - Vert-X 05E Series of dual angle/speed sensors

Novotechnik - Vert-X 05E Series of dual angle/speed sensors

Vert-X 05E Series of dual angle/speed sensors. The series features easy mounting in small and narrow spaces with a 5 mm body depth and mounting flanges with metal inserts. The sensors make measurements only 6 mm from edge of product for close-to-wall measurement applications. Vert-X 05E Series sensors measure angles from 0 to 360°, rotational speed and direction with repeatability to 0.1°.