VTuber avatar expressiveness varies wildly depending on the software and avatar artists in question. With the right software and top tier avatars, it can be quite good, but high quality avatars are extremely time consuming to create and thus expensive so only the biggest streamers tend to have those. Some agencies also force usage of less advanced agency-proprietary software to prevent talent from using the avatars without authorization.
Not quite the same as Vtuber avatars, but what you said about their software makes me think (hope) you might be able to answer a question I was wondering about the other day: is any software/models good enough yet to be able to replace the face of someone talking into a webcam with a different, photorealistic face - either that of a different existing person, or an entirely fictitious face - in real time, such that it could be used to pretend to be a different person on a live video call? Or, if not real time, how about for non-live videos, is there a tool that can do it well enough to be convincing without needing any manual editing?
And if the answer is no, how far away might it be?
(I'd be curious to play with it myself if such a thing exists and is publicly available, but the main reason I'd like to know is to keep an eye on how soon we might see faked video calls joining faked voice phone calls in the toolbox of financial scammers.)
It’s not something I’ve looked into so I’m not sure. VTuber software output can be set up to appear as a webcam which can be used in Zoom and such, so that’d be the closest that I know of.
No worries, thanks anyway
It's a bit perplexing, but 1st gen VTubers were all 3D. They evolved through natural selection into current 2D forms, only slowly growing back supplemental 3D forms.
My guess as to why is that full 3D must have been extraneous cognitive load to viewers - xkcd wouldn't have been as popular as it is now if it had been drawn somehow by Rembrandt himself. It owes its success to Randall Munroe's minimalist art style. That kinds of things.
It's probably because high quality 3d is just much more expensive to do. You can easily do all sorts of effects in the constrained environment of a 2d model that take a lot more skill to pull off in 3d.
Plus, ultimately, the anime aesthetic is a 2d thing. It's a lot harder to make a 3d model look good in a 2d art style, as a ton of anime over the years have shown.
A lot of them had 3D models and quit using it. So I doubt it had to do with the cost of making one. IMO the second one is much more likely.
It's going to wander into entirely different problems (one with a much more uncanny valley), but i'm curious to see how the field develops when facial animation systems start being able to parallel people's faces more.