-
Notifications
You must be signed in to change notification settings - Fork 283
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
psnr drop gradually #79
Comments
@menglongyue Hi, could you provide more information? e.g., the dataset you use, the command line, the full output log. |
Thanks for your reply. the training images is 3000x 2000, I set both bound and bg_radius to 16. the command line is: |
Myabe you could try to use a much larger |
ok, I will try it. I still have a question. I change the aabb_scale parameter to 4 in llff2nerf.py(default value is 2) . how to set this parameter? |
In fact |
I met similar issuse when training object with white background, some artifacts are projected to the bounding box, you may try to clip near and far or consider using the corse-to-fine sampling strategy like NeRF. |
Thanks for your excellent work. I meet with a problem. As training progresses, PSNR decreases,from 20.82 to 20.00. how to solve it ?
The text was updated successfully, but these errors were encountered: