Closed OOF-dura closed 4 years ago
You can certainly sample from the Moshed mocap data (provided here or at AMASS ), however the model presented in HMR is not generative, so you can't sample from that. You maybe interested in looking at Vposer: https://github.com/nghorbani/human_body_prior
Best,
A
HMR uses a discriminator on SMPL's pose. I would like to ask if there is a way to sample the pose. For example, you can get the corresponding pose according to the category: running pose, akimbo pose, dancing pose, sitting pose, etc.