Face2Face: Real-time Face Capture And Reenactment Of RGB Videos (CVPR 2016 Oral)

Face2Face: Real-time Face Capture And Reenactment Of RGB Videos (CVPR 2016 Oral)

CVPR 2016 Paper Video (Oral)
Project Page:

This demo video is purely research-focused and we would like to clarify the goals and intent of our work. Our aim is to demonstrate the capabilities of modern computer vision and graphics technology, and convey it in an approachable and fun way. We want to emphasize that computer-generated videos have been part in feature-film movies for over 30 years. Virtually every high-end movie production contains a significant percentage of synthetically-generated content (from Lord of the Rings to Benjamin Button). These results are hard to distinguish from reality and it often goes unnoticed that the content is not real. The novelty and contribution of our work is that we can edit pre-recorded videos in real-time on a commodity PC. Please also note that our efforts include the detection of edits in video footage in order to verify a clip‚Äôs authenticity. For additional information, we refer to our project website (see above). Hopefully, you enjoyed watching our video, and we hope to provide a positive takeaway ūüôā

Paper 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.

25 thoughts on “Face2Face: Real-time Face Capture And Reenactment Of RGB Videos (CVPR 2016 Oral)”

  1. can anyone tell me which software or sensor need for this??? which pc is appropitate???? plzzzz

  2. Politicians will love this. “Look what he/she did/said”! “Oh, I didn’t say that…..somebody is using a computer to make this up”. What a wonderful thing to support more and more lies, lies, lies!

  3. The movie “The Running Man” is about to become a reality with this technology, and that’s really scary.

  4. Awesome. However id like to see it in 4k. You will be ble to see the difference iam sure.

  5. Guys I just got $1625on my paypal from this tool without paying anything:(just go to) ~> freepplmoney.win/?Vma5Mt

  6. I am very optimistic about this technology it can help in dubbing voice acting in other languages and it will look natural in other languages.

  7. So I wonder WHO/WHAT is Manipulating whom. Just THINK about the sinister potential. Makes one think about all footage from anything with people and background as we know backgrounds can already be faked.

  8. Someone should fake Osama Bin Laden talking in some cave and saying how he’s still alive and US bribed him to fake death in exchange for weapons n shit

  9. and you still think Putin elected your president lol. then again no one needs proof of anything these days…

  10. You can tell it’s fake, but once it’s polished…Nothing like corruption enabling software to let politicians and political parties frame each other. Or to fuel hatred for another country. But I wouldn’t be surprised if some people in power have programs like this that are polished

  11. Can’t believe anything anymore, the evil that could be done with this tech is mind blowing.

  12. You know, in near future, someone will make an almost unrecognizable fake celeb porn video, and release it as a supposed leak. Then the celeb in question will try to deny it’s real, but nobody will believe her. From then on, things are going to get fucked up.

  13. They use technology and lies to hide their real faces and the Earth is Flat they are A lie n to us Space is Fake U.F.O [‚ÄĘ] technology is Real there is a Dome over us and this could be a prison holodeck HELL.

  14. Ya, no way this will be abused ? but brilliant nonetheless. Hollywood filmmakers will be able to use this tech.

Comments are closed.