search

IDEA-Research / HumanTOMATO

[ICML 2024] 🍅HumanTOMATO: Text-aligned Whole-body Motion Generation
https://lhchen.top/HumanTOMATO
Other
254 stars 6 forks source link

convert the tomato representation to SMPL-X format for visualization. #25

Open bob35buaa opened 1 month ago

bob35buaa commented 1 month ago

I would like to convert the tomato representation to SMPL-X format for visualization, similar to Figures 4 and 8 in your paper and the demo on your project page. Could you provide the necessary scripts for this? Thank you!

ours

jn-tang commented 1 month ago

Their representation is based on HumanML3D, which I think is very odd and strange. I do not know why one has to bother to run FK given gt joint rotations to get joint positions, then run IK to solve for joint rotations' 6D representation. Though the author did not give a direct conversion process, other related works are using SMPLify for solving SMPL-X parameters...

jn-tang commented 1 month ago

you can refer to these code: https://github.com/OpenMotionLab/MotionGPT/blob/main/fit.py, https://github.com/setarehc/diffusion-motion-inbetweening/blob/main/visualize/vis_utils.py

very very strange

bob35buaa commented 1 month ago

you can refer to these code: https://github.com/OpenMotionLab/MotionGPT/blob/main/fit.py, https://github.com/setarehc/diffusion-motion-inbetweening/blob/main/visualize/vis_utils.py

very very strange /

Their representation is based on HumanML3D, which I think is very odd and strange. I do not know why one has to bother to run FK given gt joint rotations to get joint positions, then run IK to solve for joint rotations' 6D representation. Though the author did not give a direct conversion process, other related works are using SMPLify for solving SMPL-X parameters...

Thanks for your reply, but all of these works use SMPLify to solve SMPL parameters, not SMPL-X parameters. Can SMPLify solve SMPL-X parameters?