search

nghorbani / amass

Data preparation and loader for AMASS
https://amass.is.tue.mpg.de/
Other
615 stars 78 forks source link

SMPL-H vs SMPL Shape Parameters #35

Open kidkych opened 2 years ago

kidkych commented 2 years ago

Hello, I've read that the SMPL-H and SMPL shape parameters are equivalent; I've also seen that for both cases the betas come in sizes of 10 or 16. Since the betas represent a PCA space, would it be correct to grab the first 10 elements from AMASS datasets that provide 16 beta parameters when we are using a SMPL model with just 10?

dmanche03 commented 2 months ago

I know it's been quite some time since this, but do you know if it worked? I have the same issue but with the 'poses' parameter. I'm trying to use the data to synthesize virtual accelerations using the SMPL model instead of SMPLH, so the length of the vector containing the poses should be 72 (3 angles 24 joints) instead of 165 (3 55). I've tried shortening the vector and keeping the first 72 values but it doesn't seem to work.