Can you spot which of these faces are real? Well, it’s a trick question, as perfectly none of these faces are all part of real human beings. Every single one in the header photo is generated by a neural network, without human input or refinement.
Researchers at AI company Nvidia have modified Generative Adversarial Network( GAN) engineering, which can create fake human faces so photorealistic that actual humen are unable to distinguish them from a genuine photograph.
The team developed their algorithm to learn patterns from over 70,000 photographs of real human faces taken from Flickr. The AI used these images to learn about different aspects of people’s faces, e.g. mane coloring, skin tone, pose, and even subtle fluctuations such as freckles, skin pores, stubble, etc.
It likewise learned to distinguish facets like the colour scheme and style of the photos, important for constructing the generated photos seem realistic.
After it had learned the characteristics of faces, and was able to separate them out, it was then taught to combine facial features to create entirely new faces, virtually indistinguishable from normal photo, except in cases of the facts of the case that the people in the photos don’t actually exist.
The faces can be combined from specific inputs, as shown in these photos generated by the study.
“We came up with a new generator that automatically learns to separate different aspects of the images without any human supervising, ” the researchers said in a video.
“The new architecture leads to an automatically learned, unsupervised separation of high-level attributes.”
This video shows how freakily smooth the code is, with seemingly human faces morphing into other completely different( also not real) faces without ever looking even briefly unrealistic.
Earlier this year, Nvidia generated another freaky bit of software that will recreate parts of photographs that have been destroyed or damaged( or, for the study, deleted on purpose ).