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

palette color #4

Open
rencq opened this issue Mar 3, 2023 · 4 comments
Open

palette color #4

rencq opened this issue Mar 3, 2023 · 4 comments

Comments

@rencq
Copy link

rencq commented Mar 3, 2023

Hi, thank you for your work!
Please, why are the colors given for the palette parameters different from the palette colors in the article such as fern?

@yuehaowang
Copy link
Owner

Hi, thank you very much for your question.
The given palettes are input to the model as an initial prior. While the palettes shown in the paper (Fig. 10 & 11) are optimized from the prior. If I understand your question correctly, that's the reason for their differences.

@rencq
Copy link
Author

rencq commented Mar 3, 2023

Hi, thank you for your answer.
But the palette I got after optimization are different in the paper, such as fern.
This is the palette I got after optimization.
1677843018058

@yuehaowang
Copy link
Owner

Hi, thank you very much for following up on this issue.

Below is the decomposition result of the fern scene that I re-trained using the provided config file. As we can see, this is consistent with the one in the paper.

image

I wonder if the raised issue is also reflected in the decomposition. Would you mind sharing your config file and dependency versions? Could you please check the data used for training? I basically downloaded data from here.

@rencq
Copy link
Author

rencq commented Mar 4, 2023

Thank you very much for your answer!

I have understood where my problem is. Thank you again for your prompt answer.

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