FVerbaas posted at 5:08 PM Mon, 1 November 2021 - #4429728

odf posted at 6:43 PM Sun, 31 October 2021 - #4429650

That's reassuring. Somehow I was under the impression that transferring morphs might be more problematic. Will have to do some tests when the time comes. A pose converter sounds like a great idea. I have no idea how to go about writing one, but pretty much all this stuff is learn-as-I-go for me, so no sweat. :-)

Maybe to talk to Nagra_00_? I spoke to him a year ago and I understand that though silent he was still active.

Good idea!

The up thing is that PoserPyhon now out of the box supports SciPy (good at doing quaternion rotations and other 3D goodies) and is open to PIP install any module from the HUGE collections available for 3.7. So there are a lot more options than in the old days.  if you can find someone who feels like making an AI based pose converter... LOL!  

I think machine learning would probably be overkill here. Modulo any potentially tricky details, the rough outline of the algorithm would be to make a pose for Antonia that matches the donor figure, convert that and the donor pose to general matrix form (or quaternions if one feels so inclined) compose the matrices and convert back to Euler angles. Not entirely unlike IK, come to think of it, but simpler.

-- I'm not mad at you, just Westphalian.