We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hey, it only takes one hour to train the same data 30,000 times with the original 3DGS.
The text was updated successfully, but these errors were encountered:
Hi, maybe more gaussians are used. Could you try to remove this line https://github.com/autonomousvision/mip-splatting/blob/main/scene/gaussian_model.py#L504 and this line https://github.com/autonomousvision/mip-splatting/blob/main/scene/gaussian_model.py#L480
Sorry, something went wrong.
It works, meanwhile PSNR decreased about 0.2?
The new densification improves NVS quite a lot. The other option is to keep this new densification metric but use high threshold to remove more Gaussians. Use 0.05 instead of 0.005 here: https://github.com/autonomousvision/mip-splatting/blob/main/train.py#L163.
No branches or pull requests
Hey, it only takes one hour to train the same data 30,000 times with the original 3DGS.
The text was updated successfully, but these errors were encountered: