search

KlabCMU / MEVA

Official implementation of ACCV 2020 paper "3D Human Motion Estimation via Motion Compression and Refinement". (Identical repo to https://github.com/ZhengyiLuo/MEVA, will be kept in sync)
https://zhengyiluo.github.io/projects/meva/
Other
5 stars 1 forks source link

How to change Virtual image？ #1

Open benpaodewoniu opened 3 years ago

benpaodewoniu commented 3 years ago

Thank you for your amazing job! Here,I have a question: I want to change virtual image and migrate actions to custom virtual image. Like a robot.

How can I do? Thank you!

ZhengyiLuo commented 3 years ago

Hi @benpaodewoniu, can you elaborate on what you mean by virtual images?

benpaodewoniu commented 3 years ago

@ZhengyiLuo In this version, the virtual image is the man on right in the video.How to change virtual model. For example, a monkey follow my actions.

ZhengyiLuo commented 3 years ago

@benpaodewoniu that would be a bit difficult to do; this repo only supports producing "human" motion. However, you can surely find a way to convert the SMPL parameters to a different rig (for instance, a monkey).

Hope that helps!