I saw some amazing work going by on the facebook group, including Matt Radford’s efforts to find a process for stylizing renders. So I thought it would be amazing to take it one step further. I haven’t done any experiments yet as I’m still unpacking from a recent move, but I thought I’d share some resources I’ve come across.
There’s tons of rendering things that we do to make flipbooks, but I’m seriously intrigued by neural nets.
Neural net program for stylizing that is fairly in reach for most scripters.
Same, but exposed to twitter.
It occurs to me that those of us who can’t code, can still send individual frames to the twitter bot until we have an animation that we can put through twixtor or slate.
Here’s a bunch of random links I use to try to get my programmer friends interested.
But if you want more basic understanding of neural nets…
oooh…nice crash course
but not completely related to photo manipulation
So my idea is to render a subset of frames for the style, but use the full frame blending vectors, like the following.
Shout out to Klemen Lozar : http://www.klemenlozar.com/frame-blending-with-motion-vectors/
The very latest from adobe labs: https://github.com/luanfujun/deep-photo-styletransfer