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

First Frame Global Position #21

Closed 0aqz0 closed 1 year ago

0aqz0 commented 1 year ago

Hi!

Thanks for sharing such an impressive job.

I have a question, if the network output is the velocity of the root joint, then where does the position of the first frame come from?

It seems that the initial position of the root joint comes from the ground truth as shown in test_online_retargeting_mixamo.py

outputB_bvh[:, :3] = gtanim.positions[:1, 0, :].copy()
wjs, rots = put_in_world_bvh(outputB_bvh.copy(), start_rots)
tjoints[:, 0, :] = wjs[0, :, 0].copy()

Looking forward to your kind reply.

rubenvillegas commented 1 year ago

Hi,

Sorry for the late reply. In order to compare the retargeted motions, we make sure that the character's root start at the same initial position. Otherwise, we cannot compare the trajectories appropriately.