Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

transform the parameters in new_joint_vecs/ to SMPL format #165

Open
coralemon opened this issue Oct 31, 2023 · 5 comments
Open

transform the parameters in new_joint_vecs/ to SMPL format #165

coralemon opened this issue Oct 31, 2023 · 5 comments

Comments

@coralemon
Copy link

No description provided.

@coralemon
Copy link
Author

hi, how to transform the parameters in the ground truth files new_joint_vecs/XX.npy (M*263) to SMPL format, (global T, R,body para)?

@coralemon coralemon changed the title transform the parameters to SM transform the parameters in new_joint_vecs/ to SMPL format Oct 31, 2023
@coralemon
Copy link
Author

And also, how to transform the SMPL para to 263 parameters?

@GuyTevet
Copy link
Owner

SMPL -> 263(humanml): use https://github.com/EricGuo5513/HumanML3D scripts
263(humanml) -> SMPL: use SMPLify optimization script

@coralemon
Copy link
Author

q1. I am wondering if the local rotation in 263 shape is the same as the definition in SMPL? It seems not, and I am confused why not using original parameters in amass?
q2. The correct SMPL rotation parameters should be generated from joints/ or new_joints/?
q3. Is the coordinate system of global translation(new_opt_cam_t) the global world system?

@GuyTevet
Copy link
Owner

GuyTevet commented Nov 1, 2023

For Q1 the answer is no. For all the rest, it will be wiser to ask https://github.com/EricGuo5513/HumanML3D for the details.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants