This New Technology Uses Artificial Intelligence To Create Portraits Of People That Don’t Exist

Published 6 years ago

A while ago, we featured an amazing new technology that was able to remove grain and watermarks from pictures, created by Nvidia. This time the technology giant is back with something even more amazing – a technology that is able to generate portraits of people that don’t actually exist using artificial intelligence (AI).

Read more

Image credits: Tero Karras, Samuli Laine, Timo Aila


The first use of this AI tool, called generative adversarial network (GAN), dates back to 2014. Back then the generated faces were grainy and colorless but after four years we finally have portraits that resemble real photographs.

It took researchers 8 weeks to train the AI to learn the various ‘styles’ of faces and produce unique ‘people’.

Here are some faces that the “Style-Based Generator Architecture for GANs” created



Turns out this technology is capable of creating more than just faces – it is even able to generate ‘fake’ interiors and vehicles.


“These datasets were trained using the setup for the duration of 70M images for ‘bedroom’ and ‘cats’, and 46M for ‘cars'”


See how this technology works in the video below

h/t: Bored Panda

Aušrys Uptas

One day, this guy just kind of figured - "I spend most of my time on the internet anyway, why not turn it into a profession?" - and he did! Now he not only gets to browse the latest cat videos and fresh memes every day but also shares them with people all over the world, making sure they stay up to date with everything that's trending on the web. Some things that always pique his interest are old technologies, literature and all sorts of odd vintage goodness. So if you find something that's too bizarre not to share, make sure to hit him up!

Got wisdom to pour?

500-

Tags

AI, AI images, AI people, AI photoshop, AI technology, Artificial intelligence, GAN, NVIDIA researchers
Tweet
7