【19 Sectret Pesonal Study (Rated 19 Secret Lesson)】

9 Sectret Pesonal Study (Rated 19 Secret Lesson)image above looks like a collage of photographs, but in fact, it's been generated by an artificial intelligence. And as real as they may look, the people in the image aren't actual humans.

In a new paper (via The Verge), a group of Nvidia's researchers explain how they've created these images by employing a type of AI, called generative adversarial network (GAN), in novel ways. And their results are truly mind-boggling.

SEE ALSO: Waymo launches self-driving taxi service, but caveats abound

The paper is titled "A Style-Based Generator Architecture for Generative Adversarial Networks" and signed by Tero Karras, Samuli Laine and Timo Aila, all from Nvidia. In it, the researchers show how they've redesigned the GAN's architecture with a new approach called "style-based design."

"Our generator thinks of an image as a collection of "styles."

"The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair)," the paper says.

In layman's terms, after being trained, the GAN produced images that are pretty much indistinguishable from photographs of real people, completely on its own.

Mashable Light Speed Want more out-of-this world tech, space and science stories? Sign up for Mashable's weekly Light Speed newsletter. By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy Policy. Thanks for signing up!

"Our generator thinks of an image as a collection of "styles," where each style controls the effects at a particular scale," the researchers explain in a video accompanying the paper. These styles are attributes such as pose, hair, face shape, eyes and facial features. And researchers can play with these styles and get different results, as seen in the video, below.

It's not just people that GAN can create in this way.

In the paper, the researchers use the GAN to create images of bedrooms, cars and cats.

Original image has been replaced. Credit: Mashable

Amazingly, the concept of GANs was introduced just four years ago by researchers from the University of Montreal.

Check the image from that paper below to see how much progress has been made since then.

Original image has been replaced. Credit: Mashable

It's easy to see this technology used in the creation of realistic-looking images for marketing or advertising purposes, for example. But it's just as easy to imagine someone using it to create fake "evidence" of events that never happened in order to promote some agenda.

At the speed this tech is progressing, it soon might be impossible to tell whether you're looking at a real photograph or a computer generated image.

---

Featured Video For You

---

This cyborg houseplant can automatically drive itself toward light

---

Topics Artificial Intelligence

• Science
• Social Good
• Shopping
• Deals
• Entertainment
• Life
• Tech
• Digital Culture

• Sméagol in the Sky
• 'To All the Boys: P.S. I Still Love You' was cute, but we must talk about the ending
• Cyberpunk 2077 maker hacked, source code of games possibly stolen
• 'Clarice' shows how deep 'The Silence of the Lambs' shadow goes
• Trump, Pumped and Dumped
• Apple talked to Nissan about Apple Car, report says
• Swiping for friends: Why managing others' dating apps is so damn fun
• Nostril hair extensions are now happening because we don't deserve nice things
• Stranger than Fiction
• 'Super Mario 3D World + Bowser's Fury' review: Two great, full games

• What if yoga pants, but with guns?
• March For Our Lives, Tide Pods, and the new way we talk about teens
• Report: Apple may have a foldable iPhone in the making for 2020
• Nvidia's self
• Apple unveils 'Schoolwork' app for iPad, 'Classroom' app for Mac
• Walmart removes 'Cosmopolitan' magazine from checkout lines
• Apple unveils updates to iWork's Pages at Chicago education event
• Man's discovery of spooky VHS tape in junk store has an unexpected twist ending
• Apple's growing list of original TV shows might arrive in March 2019
• 'Lego The Incredibles' makes family team

• Which Side Are They On?
• VR has finally found its place: porn
• ACLU's virtual postcards urge Biden to reunite separated families
• This connected tabletop gadget can measure the calories on your plate in 10 seconds flat
• The Tyranny of the Takes
• Is Facebook building its own audio
• Mastercard will support cryptocurrency payments this year
• Pandemic dating often feels like a period drama courtship
• Flint, A Complete City
• Elon Musk wants to turn Tesla Roadster into a hover car

• No Really, You Don’t Need a Weatherman
• This connected tabletop gadget can measure the calories on your plate in 10 seconds flat
• Chris Harrison steps down as Bachelor host after problematic comments
• New tech company Nothing acquires Essential, gives everyone a chance to invest
• Total Attention Deficit
• New tech company Nothing acquires Essential, gives everyone a chance to invest
• Woman Instagrams her catcallers to prove an important point
• New tech company Nothing acquires Essential, gives everyone a chance to invest
• Period Feminism
• Cyberpunk 2077 maker hacked, source code of games possibly stolen