garvita-tiwari/PoseNDF

Denoising mode representation

tommyshelby4 opened this issue · 1 comments

In the denoising mode, the input I get has dimension (num_frames, 63) which seems weird to me bearing in mind the PoseNDF uses quaternion representation as input. Shouldn't it be (num_frames, 21*4=84)?

Hi,
"denoising mode, the input I get has dimension (num_frames, 63) "
Are you talking about sample_pose.py or motion_denoise.py?
Can you please point towards the line