Creating doubt was not the goal of the fine people who created the technology highlighted in the following video, which is required viewing:
We present a novel approach for real-time facial reenactment of a monocular target video sequence…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…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.
Emphasis please: reenacted in real time.
And, to my simple eye at least, they have done a marvelous job. I am sure there is, as there always is, more work to be done. But they are well in stride.
I can imagine with ease that NBC has their checkbooks out now, ready to fund this new and profound way of “enhancing” the news. Helping certain personages say what they really meant to say must and will be seen as a great benefit at that network (among others). Do recall that TV now adds sounds of all kind (like laughter, etc.) to programs, including news programs. Enhancing and “sweetening” the video will not be seen as different.
Question: how will you be able to trust anything you see?
Answer: you will not. Not wholly. The suspicion of enhancement will always be there, lurking.