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

prune gs #29

Open
whwh747 opened this issue Dec 10, 2024 · 4 comments
Open

prune gs #29

whwh747 opened this issue Dec 10, 2024 · 4 comments

Comments

@whwh747
Copy link

whwh747 commented Dec 10, 2024

I don't seem to find any operation for removing Gaussian functions in the code. Does this method not remove Gaussian functions during the entire training process? Does it only convert dead Gaussians into alive Gaussians?

@shakibakh
Copy link
Collaborator

@whwh747 I'm sorry, but I accidentally deleted your comment in the other issue, and there doesn't seem to be a way for me to undo it!
Yes, we do not prune the Gaussians;

@whwh747
Copy link
Author

whwh747 commented Dec 10, 2024

I’m really sorry if my comment caused any misunderstanding. I just noticed the lower PSNR and casually mentioned it, without any intention to offend. Your work is great!

@whwh747
Copy link
Author

whwh747 commented Dec 10, 2024

Would this cause a surge in the number of Gaussians in the scene?

@cmh1027
Copy link

cmh1027 commented Jan 3, 2025

The growth rate of the number of Gaussians is fixed by 5% for each 100 iterations

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