AI4Animation VS mediapipe

Hi all, I've been around this scene since 2014 and we've seen some incredible mods over the years. If anyone is familiar with the AI scene recently, you may have came across a paper called DeepPhase which allows for fully procedural, unique animations in realtime. It's a long shot, but is anyone here familiar with the animation pipeline for Skyrim - and whether it would be even feasible to implement this paper into the game? This is just theorycrafting or spitballing an idea, but I'd love to have a discussion here!

character motion being the same old animations, just done/interpolated better

the only advancement I know of which got close to be implemented in games is https://github.com/sebastianstarke/AI4Animation (I think Sebastian worked with EA or some other big company at some point) - still haven't played anything using this though

Here's the paper for one of them: Phase Function Neural Networks. In the paper you can also find names of other algorithms and look up their associated papers. The reason I single out this one is because the author also uploaded their original Unity implementation.

(bonus: here's an excellent and comprehensive gdc talk from ubisoft going over their tech and how it helped them address the insane complexity in their assassin's creed games. second bonus: the guys that did that basketball demo in the 2 minute papers video have their work in a github repo, if you're feeling spry)

mediapipe/docs/solutions/pose.md at master · google/mediapipe · GitHub

Today, we announce MediaPipe diffusion plugins, which enable controllable text-to-image generation to be run on-device. Expanding upon our prior work on GPU inference for on-device large generative models, we introduce new low-cost solutions for controllable text-to-image generation that can be plugged into existing diffusion models and their Low-Rank Adaptation (LoRA) variants.

You can just grab the TFLite version! https://github.com/google/mediapipe/blob/master/docs/solutions/models.md

I believe Google already released transformers under an apache 2 license with a patent grant:

https://github.com/google/mediapipe/blob/master/mediapipe/mo...

I was going to say that I like the MediaPipe Selfie Segmentation model for doing this sort of thing in a web page, but I've just noticed (when getting the GitHub link[1]) that Google have marked the code as legacy[2] ... no idea if the new solution is better/easier to use[3].

For what it's worth, my CodePen using the old model is here: https://codepen.io/kaliedarik/pen/PopBxBM

[1] - https://github.com/google/mediapipe/blob/master/docs/solutio...

[2] - "Attention: Thank you for your interest in MediaPipe Solutions. As of April 4, 2023, this solution was upgraded to a new MediaPipe Solution."

[3] - https://developers.google.com/mediapipe/solutions/vision/ima...

I have used mediapipe very successfully in multiple projects and it's very easy to get running. You can choose from many different vision tasks including hand landmarks ( https://github.com/google/mediapipe/blob/master/docs/solutions/hands.md )

I found MediaPipe's Face Mesh and was impressed with how simple it was to get going, but it just gives you the landmark points and I've not gone any further yet.

We've trained ControlNet on a subset of the LAION-Face dataset using modified output from MediaPipe's face mesh annotator to provide a new level of control when generating images of faces.

Medipaipe library link: https://mediapipe.dev/