Some folks at NVIDIA have developed a "style-based generator architecture for generative adversarial networks", borrowing from "style transfer literature". It has been demonstrated to generate remarkably realistic (and fictitious) human faces. As impressive as it is, it's not obvious the extent to which the demonstration of this architecture is like a little old lady who only drove it to church on Sundays. Regardless, it looks like the AI overlords can now have alleged supermodel girlfriends in Canada too:
The video demonstration is at https://www.youtube.com/
Their explanation/description is at https://arxiv.org/pdf/1812.04948.pdf
(Score: 2) by Nerdfest on Friday December 14 2018, @06:33PM (3 children)
I think I'm a "Negative Face".
(Score: 2) by VLM on Friday December 14 2018, @08:19PM (2 children)
"Resting Sysadmin Face"
Regardless of jokes about pr0n and fake news this would be perfectly applicable to yet another remake of Thomas the Tank Engine.
Also "Thomas the Dank Engine" (probably NSFW for visual, audio, and intellectual reasons), not a typo, theres some pretty good youtubes of rather amateur-ish manual implementations of this technology.
(Score: 2) by takyon on Friday December 14 2018, @08:37PM (1 child)
https://www.youtube.com/watch?v=ETfiUYij5UE [youtube.com]
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 2) by VLM on Friday December 14 2018, @09:09PM
The Thomas theme song goes well with everything.