Tuesday, December 27, 2016

Voiceover/Face 2Face ... Fake News writ large



Voiceover takes on a whole new meaning with this upcoming app where fake speech becomes just an afterthought using code as powerful as this.

When recording voiceovers, dialogue, and narration, wouldn’t you love the option to edit or insert a few words without the hassle of recreating the recording environment or bringing the voiceover artist in for another session? #VoCo allows you to change words in a voiceover simply by typing new words. Have to hear it to believe it? Check out a live demo (above) using a recording of co-host Jordan Peele’s voice.

Now, combine Voiceover with Face2 Face. Now, the Fake News fun really begins, don't you think?



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.

Minitrue anyone?

No comments: