search

rubenvillegas / cvpr2018nkn

Tensorflow implementation of the CVPR 2018 paper: Neural Kinematic Networks for Unsupervised Motion Retargetting
https://sites.google.com/umich.edu/nik
Other
240 stars 42 forks source link

Why the cycle loss work #7

Closed henrylovedesign closed 4 years ago

henrylovedesign commented 4 years ago

Hi, the autoencoder loss and cycle loss described in the paper should has a global optimal solution that is just copying quaternions and velocity, but why the GRU model learn something different?

rubenvillegas commented 4 years ago

This was answered in the previous question. In the future, make sure you don't submit duplicate issues.