To be fair, stop motion animating is fucking time consuming and such an art. Let alone for first person camera views AND third person
Having an AI quickly generate a hand wave motion etc and convert to first person and vice versa would save hours and hours of capping one frame at a time
Most digital animation done by hand isn’t done in the stop motion/frame-by-frame way, It’s done with key frames that are interpolated between. That’s not to say it isn’t still super time consuming (especially when done well).
Yes! You nailed it
A lot of motions still need to be scrubbed frame by frame and adjusted if any of the key frames dont interpolate cleanly
It’s one of those menial tasks that AI could actually specialize and hugely assist in for simple repetitive animations. Or imagine have a custom animation that the AI/ML uniquely generates the key frames on the fly. Talking distant future but every animation could be potentially be entirely unique everytime you see it
I could see a system where you very loosely define a handful of keyframes, give it some kind of description for what your looking for, and then the model fills in the rest for you. It almost certainly would still require some tweaking on the artists part, but I think a huge benefit is that AI can be non-deterministic. If you don’t like what you got you can just run it again without changing inputs. Maybe save multiple runs and manually combine all the best elements. Lots of opportunity.
That’s not true, with motion capture you are recording an actor do all the motions and fixing whatever is necessary. It’s different to pose to pose animation.Removed by mod
Turns out I can’t read
While I’m not going to slag this dude because I know nothing about him personally, this isn’t a case of it being “time for a revolution” in those aspects, the revolution already fucking happened. Case in point, Embark Studios.
https://medium.com/embarkstudios/the-content-revolution-to-come-f2432dc6a434
https://medium.com/embarkstudios/one-click-photogrammetry-17e24f63f4f4
https://medium.com/embarkstudios/transforming-animation-with-machine-learning-27ac694590c
Those pieces were all published 3-4 years ago. Rockstar isn’t going to be taking first steps here, they’re walking in someone else’s footprints.
do these articles exist on a less cancerous source?
Unfortunately not that I’m aware of. They’re pieces written by Embark employees to Embark’s Medium blog, I guess they use them for hosting or something idk how corporate Medium works.
Common indie W
E: I don’t like getting silent downvotes. Feels like a missed chance to have a totally unproductive flame war with a stranger.
“E”. How much time did you save with that? Three fucking letters and I have to be sitting here trying to figure out what the fuck “E” means. Fuck you, and I hope you take this personally.
Sorry, not much to add to the topic at hand, but I figure that’s not a requirement for a flame war.
Sorry Mr “Terminally Online”, I don’t have the time to write out “edit”! I have a job and a life and my time is valuable, but I wouldn’t expect a simpleton like yourself to understand that.
!just adding to the war, dont mind me!<
It means edit
deleted by creator
Even in 2024 inverse kinematics are still kind of a nightmare to get right. I would really welcome some AI that just fixes my janky animations.
Something like this?
I wonder how much things like drift and recursion (ai training on its own data) would have on applications like this. I assume it’s like most and it it would just produce nonsense. But since it would likely result in cuts to the animation staff, I’d think recovery from model collapse would be harder since getting new data takes time, staff resources that would be hard build up while in the middle of development.
develop the productive forces
for more anatomically-correct horses
And this will lead to games with more animations and better animations, not a loss of animation jobs. Might lower the skill ceiling a bit, but there are always going to be bespoke animations requiring much more manual work, especially for non-humanoids and objects. Animators will be able to focus their time more broadly.
An article based on a rumor someone else heard.
Yeah
