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

Is it possible to fit scan mesh without landmark? #48

Open
dragonylee opened this issue Oct 10, 2023 · 3 comments
Open

Is it possible to fit scan mesh without landmark? #48

dragonylee opened this issue Oct 10, 2023 · 3 comments

Comments

@dragonylee
Copy link

Thanks for your work!
I am using your code fit_scan.py to fit a mesh with arbitrary topology. It's hard to generate landmarks for all inputs. Is there any way to fit it without landmarks please?

@bbakpil
Copy link

bbakpil commented Apr 11, 2024

Hi, did you get any ideas/solutions?

@dragonylee
Copy link
Author

Hi, did you get any ideas/solutions?

No, so when I was comparing them, I explained that their method requires providing landmarks.

@TimoBolkart
Copy link
Collaborator

Fitting the model to a scan minimizes follows some iterative closest point scheme, which alternates between computing correspondences between each scan vertex and the FLAME model mean, and minimizing the distance between these points in correspondence. As ICP-based methods converge only locally die to the unknown correspondence, a good initialization is required for this optimization. One common way is to assume the correspondence for few keypoints to be given. Without these keypoints, you will need to find some other way to initialize the optimization to get good initial correspondences for the ICP to work.

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

3 participants