From TechCrunch
A new paper published by Disney Research in partnership with ETH Zurich describes a fully automated, neural network-based method for swapping faces in photos and videos — the first such method that results in high-resolution, megapixel resolution final results according, to the researchers. That could make it suited for use in film and TV, where high-resolution results are key to ensuring that the final product is good enough to reliably convince viewers as to their reality.
The researchers specifically intend this tech for use in replacing an existing actor's performance with a substitute actor's face, for instance when de-aging or increasing the age of someone, or potentially when portraying an actor who has passed away. They also suggest it could be used for replacing the faces of stunt doubles in cases where the conditions of a scene call for them to be used.
The mouse has the paper
(Score: 4, Interesting) by takyon on Thursday July 02 2020, @03:38AM (2 children)
I was going to submit this but misplaced it.
Given Disney's habit of "fixing" up films on Disney+ [soylentnews.org], maybe they will use this to redo some shots in Rogue One [wikipedia.org].
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Thursday July 02 2020, @07:29PM (1 child)
The CG at the end of that movie was crap, with crap being the operative word [deseret.com] when it comes to Disney SW. They're best off tucking the entire tired franchise into hypersleep for the rest of the decade.
(Score: 3, Insightful) by PartTimeZombie on Thursday July 02 2020, @11:51PM
I couldn't agree more. Of course they won't because they paid too much for the rights, and have to get a return on investment.
I rather enjoyed Rogue One. It's hardly a classic, but is (in my view) the best Star Wars in a while. The Last Jedi is also the last Star Wars movie I will watch.
From what I understand the latest couple have not been improvements either, so I won't even bother pirating them.