search

SimonGiebenhain / NPHM

[CVPR'23] Learning Neural Parametric Head Models
https://simongiebenhain.github.io/NPHM/
Other
231 stars 18 forks source link

Fitting and model latent code question #9

Closed wengjincheng closed 1 year ago

wengjincheng commented 1 year ago

Hi,

Thanks for your great work, I have one question that whether I just need to fit Head points cloud to get global id latent code and expression latent code? But the local id latent code is not needed?

SimonGiebenhain commented 1 year ago

Hi,

the id latent code is composed of a global part and a multiple local latents. When attempting to reconstruct a head based on a point cloud, you have to fit the identity code (including both local and global part), as well as, the expression code (for expressions everything is modeled in a single global code and there are no local codes)

wengjincheng commented 1 year ago

Hi,

the id latent code is composed of a global part and a multiple local latents. When attempting to reconstruct a head based on a point cloud, you have to fit the identity code (including both local and global part), as well as, the expression code (for expressions everything is modeled in a single global code and there are no local codes)

Thanks for your clear reply