Re:Live3D: Collaborative Neural Rendering Using Anime Charac...
by mike233 on Friday August 05, 2022 @05:15AM
(#32353581)
Simple but effective.
CINN looks like a batch-wise pooling.
Reviewers today prefer fancy Transformer or NeRF stuff, but the performance may not be that different from those old-school models with some modifications.
To me, this looks like great craftsmanship: They have built a working implementation where others failed. And they found a way to cheaply generate lots of training data. But sadly, research optimizes for novelty, not for usability.
CINN looks like a batch-wise pooling.
Reviewers today prefer fancy Transformer or NeRF stuff, but the performance may not be that different from those old-school models with some modifications.
https://github.com/transpchan/Live3D/issues/1
and here's the paper review notes:
https://github.com/transpchan/Live3D/blob/main/eccv.pdf
which complains that it's too similar to
https://anr-avatars.github.io/
and
https://ai.facebook.com/research/publications/continuous-sur...
To me, this looks like great craftsmanship: They have built a working implementation where others failed. And they found a way to cheaply generate lots of training data. But sadly, research optimizes for novelty, not for usability.