Comment by mgraczyk | Hacker News Reader

Comment by mgraczyk | Hacker News Reader

I remember watching an interview with the creators of South Park in which they described the transition from animating using cardboard cutouts to a system with CorelDraw and other pieces of software which helped speed up the process. The bulk of the efficiency improvement came from carefully defining all the frequently used objects (characters, houses) once with movable components, and reusing those objects in the per-episode animation pipeline.

I can easily imagine an animation system like the one presented here enabling another massive improvement in animation efficiency. In the same way animation software allowed South Park to reuse pre-drawn objects, a deep learning system could enable south park to carefully define the entire drawing style just once, then generate complete episodes based on simple story boards and animation directives. Fortunately, South Park already has a significant amount of training data available, specifically every South Park episode yet produced.

An app that would let someone quickly animate a some dialogue in the style of South Park/The Simpsons/Family Guy would be an instant best seller. It would become the "Supernormal" of the late 20-teens. You could even do it by only outputting the equivalent of Wally Wood's 20 panels that always work.

http://www.comicbookscriptarchive.com/archive/panel-1/panel-...

https://xkcd.com/1205/

This would be a great proof of concept, in fact someone should work on this as a pet project, but I doubt it would be worth as an investment in the rest of the show's run. I bet they don't spend a lot of time on the basic animation anymore, and instead focus mostly now on one-off set pieces and visual effects

Another interesting problem would be the generation of filler pictures (I don't know the correct term). Normally there is a person who draws keyframes at a much lower framerate. Other animators then fill in the frames between to increase the framerate.

It's called in-between. There is certainly an art form of its own, for a simple mechanical interpolation won't produce visually pleasing animation. Disney has some research on parameterizing in-betweening. These days 2D animation are replaced with 3D and the art of 2D in-betweening might be lost in future. It'll be interesting if DN can learn animation styles from existing footage (e.g. Kanada-style).

They're called inbetweens or tweens. According to recent HN article, they are outsourced to South Korea. Generating them with algorithm would be interesting, but often incorrect and against artist wishes. For example, objects in motion sometimes needs to be blurred; some characters need to have ghost duplicates; shapes get distorted and exaggerated.

I think at this moment it is not possible to instruct algorithm to take additional suggestions (artist ideas) into consideration when creating output image.

there's this https://www.youtube.com/watch?v=zICe4hYAJBE

That's the problem with animation using bitmaps (or physical artwork): the in-betweens have to be manually drawn. Hence much animation is outsourced to studios - typically in Korea, and occasionally Japan - consisting of armies of animators and artists.

With vector graphics - where the lines and fills are mathematical objects - automatic 'tweening' becomes possible. Anime Studio (http://my.smithmicro.com/anime-studio-2D-animation-software....) is the zenith of this tech; there's also Synfig (http://www.synfig.org/cms/) and CACANi (https://cacani.sg/).

In Anime Studio it's possible to add all kinds of effects (including filter effects and motion blur) to animations, and to mix pure vector animation with cutout, or even frame-by-frame, animation.

I used to play around with just such a tool back in the 80s and 90s called Fantavision

https://en.wikipedia.org/wiki/Fantavision

There's a lot of work to take advantage of perceptual quirks of human vision that happens in tweens by humans that these algorithms don't account for (at least last I knew).

Sometimes a perfect interpolation, or even something based on a physical model doesn't feel right, isn't what is expected.

Disney and American TV shows have pretty mechanical approaches to this, and you can usually tell which are the keyframes when the characters seem to settle into a pose before starting a new one. But not everyone draws that way - try and find them in End of Evangelion!

https://www.youtube.com/watch?v=iounOj1VRUU

Reply on news.ycombinator.com