As with all artificial intelligence, there’s a definite creep factor to a new system that can recreate lifelike motion from just one frame of a person’s face.

The system was developed by researchers at the Samsung AI Center. It’s a new method of applying facial landmarks on a source face to the facial data of a target face, making the target face do what the source face does, reports TechCrunch.

This isn’t entirely new and feels a bit like some next-level Deepfake.

We can already make a face in one video reflect the face in another in terms of what the person is saying or where they’re looking. But most of these models require a considerable amount of data, for instance a minute or two of video to analyze.

The new paper by Samsung’s Moscow-based researchers, however, shows that using only a single image of a person’s face, a video can be generated of that face turning, speaking and making ordinary expressions — with convincing, though far from flawless, fidelity.

Skip ahead to 5:00 to see famous portraits, including the Mona Lisa, brought to life:

This is achieved by frontloading the facial landmark identification process with a huge amount of data, which makes the model really good at finding the parts of the target face that correspond to the source.

The more data it has, the better, but it can do it with one image — called single-shot learning — and get away with it. That’s what makes it possible to take a picture of Einstein or Marilyn Monroe, or even the Mona Lisa, and make it move and speak like a real person.

At the moment, you can only animate the head and torso, but it probably won’t be long before the rest of the body is mapped and animated too.

Now we sit back and wait for someone to turn it into porn, as they did with Deepfake.

Because when it comes to humans, where there’s innovation, there’s masturbation.

[source:techcrunch]