Photoshop made it super easy to fake-it-while-you-make-it, especially in the unrealistic world of beauty expectations that leave so many naturally beautiful humans insecure.

So eventually someone would find a way to automate itself, and now it already has.

It all started three years ago, reports Quartz…:

“After an argument at a bar with some fellow artificial intelligence researchers, Ph.D student Ian Goodfellow cobbled together a new way for AI to think about creating images.”

The heated discussion inspired a pretty simple idea: one algorithm tries to generate a realistic image of an object or scene, while another tries to decide whether it’s real or fake.

Shoot to the future and you have GANs, or “generative adversarial networks,” a new cornerstone of AI research that Goodfellow and Google are studying in-depth already. Other tech leaders such as Adobe and Facebook are also calculating their own piece of the pie.

What does this mean, and how can it be separated from celebrity claptrap? Quartz reckons that:

Uses for data generated this way span from healthcare to fake news: machines could generate their own realistic training data so private patient records don’t need to be used, while photo-realistic video could be used to falsify a presidential address.

GAN-generated imagery has always seemed more distant than the future, but recent research from Nvidia shows that it can now be used to create high-resolution, realistic images of celebrities, scenery and objects:

GAN-created images are also already being sold as replacements for fashion photographers—a startup called Mad Street Den told Quartz earlier this month it’s working with North American retailers to replace clothing images on websites with generated images.

Take a look:

The accuracy of Nvidia’s results are thanks to a library of 30 000 celebrity images that are used to train algorithms. The more data, the better! Quantity beats quality.

But…

The images aren’t perfect. Some test images show women with only one earring, or a horse with a head on both sides of its body.

Now, more than ever, is the time to take a closer look at what the media shows us. It’s not what it looks like, baby.

[source:quartz]