“Deep Video Portraits” can put words in your mouth

Part of me says, “What great new tools for expressive video editing!”

The other part says, “This will not end well…”

[W]e are the first to transfer the full 3D head position, head rotation, face expression, eye gaze, and eye blinking from a source actor to a portrait video of a target actor… [W]e can reenact the full head using interactive user-controlled editing, and realize high-fidelity visual dubbing.

NewImage

[YouTube] [Via Jeremy Cowles]

4 thoughts on ““Deep Video Portraits” can put words in your mouth

  1. This was so beautifully foreshadowed by Walter M. Miller Jr in his novella “The Darfsteller,” which won him the first Hugo award in 1955, when I was an avid reader of Astounding Science Fiction and the other great old pulps. It stuck in my head permanently, as did a lot of those “first gen” SF stories. Concepts nobody had explored before. The whole story is based on 1940’s technology, so it must have been quite a stretch for him to imagine the final days of the LAST living actor.

Leave a Reply

Your email address will not be published. Required fields are marked *