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.

Sign up for GitHub

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

Jump to bottom

2D Landmarks from FLAME model #31

Open

emlcpfx opened this issue Jan 21, 2025 · 0 comments

emlcpfx commented Jan 21, 2025

Hi, I have really a really strong 3D track of a FLAME model on some footage.
https://www.linkedin.com/posts/ericlevy_were-doing-rd-on-a-new-machine-learning-activity-7262912859997716481-D4Do?utm_source=share&utm_medium=member_desktop

How can I derive the 2D landmarks from this like how SPIGA does, where they follow the contour of the face?

Could I use the pose data from the other repo to replace the pose data that SPIGA comes up with, and get a better result?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment