Computer networks are getting pretty good at synthesizing video from fragmentary sources, as shown in this latest production from Two-Minute Papers (link to YouTube).
Photo-realistic expressions at right are generated
purely from the line drawings at left. Source
The generative adversarial networks can effectively create video from animated line drawings, as in the still frame above. They're also getting better at classifying the elements of a scene into its various components and translating one class of objects into another. So, for example, a tree-lined street can be changed so that it's lined with buildings instead, or vice versa.
Kate, yes, that comment seemed to be offering hacking services. A little off topic. ...and yes, CGI has been making some amazing progress. Normally I would have thought those line drawings of faces were made from the photo-images, but it was the other way around.
Well, your first comment was ...interesting, James!
ReplyDeleteI just want to say I was astonished at how far cgi has come!
Not comment. I meant commentator.
ReplyDeleteKate, yes, that comment seemed to be offering hacking services. A little off topic.
ReplyDelete...and yes, CGI has been making some amazing progress. Normally I would have thought those line drawings of faces were made from the photo-images, but it was the other way around.