Artificial intelligence, in recent years, has become too realistic and will continue to improve and evolve as time goes on.
Samsung’s AI Centre’s latest research is focused on making a system that can recreate lifelike motion from one single frame of a person’s face.
We could simply use a still image or painting and make it appear as if it is speaking.
According to TechCrunch, the technology uses Generative Adversarial Network which puts two models against one another, with “one trying to fool the other into thinking what it creates is real”.
The system has not fully been perfected and so far only works on faces and upper torso’s however; when it works it does a dangerously realistic job.