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

How to learn trans? #33

Open
lllll8 opened this issue Nov 27, 2023 · 2 comments
Open

How to learn trans? #33

lllll8 opened this issue Nov 27, 2023 · 2 comments

Comments

@lllll8
Copy link

lllll8 commented Nov 27, 2023

The groundtruth of SMPL trans parameters range varies widely for each dataset, How to let the network learn the correct trans, combined with the focal and the princpt to complete the correct projection? I noticed you set focal = 5000, princpt = 256/2, how to understand this value? Thank you!!

@hongsukchoi
Copy link
Owner

Hi,

The groundtruth of SMPL 'trans' parameters are not used for training, since we crop the image around the target person.

The focal length is just a default number, which can be changed.
THe princpt is the center of the cropped and resized image.

focal = (5000, 5000)  # virtual focal lengths
    princpt = (input_img_shape[1] / 2, input_img_shape[0] / 2)  # virtual principal point position

@lllll8
Copy link
Author

lllll8 commented Nov 29, 2023

Thank you for your reply. I understand that you say about the meaning of virtual focal and principal point. this project is so amazing.

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