search

Nicholasli1995 / EvoSkeleton

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"
https://arxiv.org/abs/2006.07778
MIT License
332 stars 44 forks source link

the input channel order to_spherical calculation #17

Closed we1314love closed 3 years ago

we1314love commented 3 years ago

hello, thanks for your outstanding work. I am learning the evolution part and had some questions about the to_spherical calculation.

in EvoSkeleton/libs/skeleton/anglelimits.py line179-192 is the function of to_spherical(xyz), and I have one questions:

  1. according to the code, before calling to_spherical(), the skeleton has been re_order to xzy, while the formula of to_spherical use the xyz order, so if the skeleton in xzy order input to to_spherical, can we still get the right result?
Nicholasli1995 commented 3 years ago

Hi, I remembered that the original PosePrior used inputs that are in xzy order, so I did that before computing local orientation. You can refer to the matlab implementation of the original paper for details and ask further questions here.

Nicholasli1995 commented 3 years ago

Closing inactive issues that already have answers. Re-open if needed.