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

What is the basis for your control point selection? #49

Open
chengbilian opened this issue Oct 3, 2024 · 3 comments
Open

What is the basis for your control point selection? #49

chengbilian opened this issue Oct 3, 2024 · 3 comments

Comments

@chengbilian
Copy link

          For your data, you need to manually select the control points to calculate anthropometric measurements and calculate your own PCA representation.

Originally posted by @zengyh1900 in #48 (comment)

@chengbilian
Copy link
Author

Hello,What is the basis for your control point selection?

@jpcurbelo
Copy link

jpcurbelo commented Oct 3, 2024

Hi @chengbilian. We had a bit of a discussion on how to define and extract the CP and how to extract the measurements from the CP. I hope that helps.

@jpcurbelo
Copy link

Also, in case you are interested, you might take a look at my repo (based on @zengyh1900's repo) and paper. Thanks.

In summary, in the repo you can find the code to generate the 3D avatar from two full-body images (front and side) + subject height + gender.

  1. The silhouettes are extracted from the images.
  2. Extractor: a NN that extracts 8 measurements from the Silhouettes+Height+Gender
  3. Imputer: The "missing" measurements are imputed to complete a set of 21 measurements.
  4. Reshaper: Minor edits were implemented to @zengyh1900's code and it was trained by using a different set of 21 measurements. This is used to generate the 3D avatar.

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