atseajournal
I know hand-drawn 2D is its own beast, but what's your thought on using 3D datasets for handling the occlusion problem? There's so much motion-capture data out there -- obviously almost none of it has the punchiness and appeal of hand-drawn 2D, but feels like there could be something there. I haven't done any temporally-consistent image gen, just playing around with StableDiffusion for stills, but the ControlNets that make use of OpenPose are decent.
3D is on my mind here because the Spiderverse movies seemed like the first demonstration of how to really blend the two styles. I know they did some bespoke ML to help their animators out by adding those little crease-lines to a face as someone smiles... pretty sure they were generating 3d splines however, not raster data.
Anyway, I'm saving the RSS feed, hope to hear more about this in the future!
"I convert folks all the time. I get zero a year readers to an average of 6 to 10 a year. Mostly because i used to hate reading until i got converted as well. I know the pain points."
I used to read 30-ish novels a year, and now it's more like 4. Would love to get back on the horse, I'm sure there are plenty of others. Finding fun books to read is tough.
As for post 2, 3, 4...? I dunno, but I'm on Twitter at atseajournal, and happy to hear about whatever.
Have you got a blog or anything like that?