时间:2025-04-26 13:27:39 来源:网络整理编辑:焦點
The image above looks like a collage of photographs, but in fact, it's been generated by an artifici
The 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 aboundThe 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.
"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.
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.
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.
TopicsArtificial Intelligence
Mom discovers security cameras hacked, kids' bedroom livestreamed2025-04-26 13:25
Intel's self2025-04-26 13:16
The artist blowing people's minds in virtual reality2025-04-26 13:06
Dust off your dream journal: 12 of the world's best hotel pools2025-04-26 12:39
Cat gets stuck in the most awkward position ever2025-04-26 11:57
'Rogue One' steals away with $155 million at the domestic box office2025-04-26 11:43
Augmented reality app from IBM and NY Times tries to make history fun2025-04-26 11:16
The ad block apocalypse didn't arrive and doesn't look like it's going to2025-04-26 10:58
Plane makes emergency landing after engine rips apart during flight2025-04-26 10:51
15 times Carpool Karaoke was the perfect antidote to 20162025-04-26 10:43
Singapore gets world's first driverless taxis2025-04-26 13:17
This airline sacrificed a goat on the tarmac before its flight took off2025-04-26 13:15
Wendy's Twitter serves up a slice of sassy when their motto is questioned2025-04-26 13:13
It's not just you, Tumblr went down today2025-04-26 13:02
Whyd voice2025-04-26 12:14
Pioneering bionic eyes are being given to 10 blind people2025-04-26 11:48
Nate Silver sends out apocalyptic tweet just in time for the holidays2025-04-26 11:46
World map proves basically every country has a terrible tourism slogan2025-04-26 11:31
U.S. pole vaulter skids to a halt for national anthem2025-04-26 10:53
WhatsApp group administrators not liable for content: Indian court2025-04-26 10:47