SoylentNews is people
SoylentNews
Submitted via IRC for SoyCow0152
A new deep learning algorithm can generate high-resolution, photorealistic images of people — faces, hair, outfits, and all — from scratch.
The AI-generated models are the most realistic we've encountered, and the tech will soon be licensed out to clothing companies and advertising agencies interested in whipping up photogenic models without paying for lights or a catering budget. At the same time, similar algorithms could be misused to undermine public trust in digital media.
The algorithm was developed by DataGrid, a tech company housed on the campus of Japan's Kyoto University, according to a press release.
In a video showing off the tech, the AI morphs and poses model after model as their outfits transform, bomber jackets turning into winter coats and dresses melting into graphic tees.
Specifically, the new algorithm is a Generative Adversarial Network (GAN). That's the kind of AI typically used to churn out new imitations of something that exists in the real world, whether they be video game levels or images that look like hand-drawn caricatures.
Source: https://futurism.com/ai-generates-entire-bodies-people-dont-exist
Generative Adversarial Network
(Score: 5, Insightful) by bob_super on Monday May 06 2019, @05:08PM (1 child)
You don't need any advanced tech for that.
Hold the rally in front of a sparsely populated room, choose a few camera angles through the people who are there.
If anyone points out the room was mostly empty, deny and call them "Fake News". Any picture showing the empty room are just partisan photoshops.
Nah. That would never work. People aren't that dumb...
(Score: 0) by Anonymous Coward on Monday May 06 2019, @06:20PM
If only