时间:2025-04-03 10:46:42 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
'The Flying Bum' aircraft crashes during second test flight2025-04-03 10:46
Wordle today: Here's the answer, hints for May 262025-04-03 09:53
Hands on with Stage Manager in Apple's macOS Ventura2025-04-03 09:52
The best time travel movies you can watch right now2025-04-03 09:50
Daughter gives her 1002025-04-03 09:49
Bitcoin and other cryptocurrencies are on a downward spiral. Why?2025-04-03 09:32
Twitter to Elon Musk after he pulled out of buyout deal: 'We'll see you in court'2025-04-03 09:23
Airbnb horror stories are taking over Twitter2025-04-03 08:33
Singapore rolls out video2025-04-03 08:17
WhatsApp rolls out emoji reactions2025-04-03 08:11
This 'sh*tpost' bot makes terrible memes so you don't have to2025-04-03 10:41
'Players' on Paramount+: The creators explain their less2025-04-03 10:33
Hands on with Stage Manager in Apple's macOS Ventura2025-04-03 10:05
Airbnb horror stories are taking over Twitter2025-04-03 10:05
WhatsApp announces plans to share user data with Facebook2025-04-03 09:53
Predators are growing hungrier in the rapidly heating ocean2025-04-03 09:09
What are NFTs? Everything you need to know.2025-04-03 09:07
'Players' on Paramount+: The creators explain their less2025-04-03 09:02
Samsung Galaxy Note7 teardown reveals the magic behind the phone's iris scanner2025-04-03 08:26
This simple air fryer French fry recipe will give you the perfect homemade side dish2025-04-03 08:08