CLIP-Score Calculation #445

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

Open

LeoHsuProgrammingLab opened this issue Apr 30, 2025 · 0 comments

LeoHsuProgrammingLab commented Apr 30, 2025

Hi, thank you for the amazing work of SV4D. I have a question about if the reported metric CLIP-s is calculated by:

The generated text and image pair
The similarity of GT image and generated image like Consistent4D

Additionally, if it is the first one, how do you decide which text is reliable?
Thank you!

Sincerely,
Chih-Chuan

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