As we get better at making, faking, and manipulating human faces with machine learning, one thing is abundantly clear: things are going to get ~freaky~ fast.
Case in point: this online demo hosted (and, we presume, made) by web developer AlteredQualia. It combines two different research projects, both of which use neural networks. The first is DeepWarp, which alters where subjects in photographs are looking, and the second is a work in progress by Mike Tyka dubbed Portraits of Imaginary People. This does exactly what it says on the tin: feeding a generative neural network with a bunch of faces and getting it to create similar samples.
Combine it with a tool for making eyes follow your cursor, and you have a healthy slice of the uncanny valley, the phenomenon of human perception where something looks human but not quite human enough. Here are some more examples from Tyka’s project:
As we’ve written in the past, this sort of image is only going to become more common as machine learning and AI proliferate. Neural networks are easy enough for lots of people to play with, and are improving all the time. In this case, that’s going to mean more and more near-photorealistic and photorealistic fake humans. If the artificial intelligence boom we’re currently experiencing has to have a face, this is it.