Nvidia’s scary AI generates humans that look 100 % real!
The technology works so well that we can expect synthetic image search engines soon - just like Google’s, but generating new fake images on the fly that look real. Yes, you know where that is going - and sure, it can be a lot of fun, but also scary.
According to Nvidia, its GAN is built around a concept called “style transfer”. Rather than trying to copy and paste elements of different faces into a frankenperson, the system analyzes three basic styles - coarse, middle, and fine - and merges them transparently into something completely new.
Coarse styles include parameters such as pose, the face’s shape, or the hairstyle. Middle styles include facial features, like the shape of the nose, cheeks, or mouth. Finally, fine styles affect the color of the face’s features like skin and hair.
According to the scientists, the generator is “capable of separating inconsequential variation from high-level attributes” too, in order to eliminate noise that is irrelevant for the new synthetic face.
For example, it can distinguish a hairdo from the actual hair, eliminating the former while applying the latter to the final photo. It can also specify the strength of how styles are applied to obtain more or less subtle effects.
Not only is the generative adversarial network capable of autonomously creating human faces, but it can do the same with animals like cats. It can even create new cars and even bedrooms.
Nvidia’s system is not only capable of generating completely new synthetic faces, but it can also seamlessly modify specific features of real people, like age, hair or skin color.
The applications for such a system are amazing. From paradigm-changing synthetic free-to-use image search pages that may be the end of stock photo services to people accurately previewing hair styling changes; and of course, porn.
However, the potential for fraud is immeasurable, and the possibility of corrupt governments using this technology to further encroach on the freedom and individuality of people cannot be dismissed.
Some technology must be devised to counteract this new threat.
