Describe the bug
I’m trying to limit the region of interest for instant-ngp as much as possible to avoid unnecessary computation. However, when I make it very tight around the object, it fails to predict any color. When I enlarge the region of interest, it starts predicting colors again, which is puzzling to me, since I can clearly see the "wasted space".
Expected behavior
Whenever the tight region of interest is used, the model fails to predict any rgb at all, while with the not so tight (simply 2x) the model quickly converges.
Describe the bug I’m trying to limit the region of interest for
instant-ngp
as much as possible to avoid unnecessary computation. However, when I make it very tight around the object, it fails to predict any color. When I enlarge the region of interest, it starts predicting colors again, which is puzzling to me, since I can clearly see the "wasted space".To Reproduce Steps to reproduce the behavior: Check out this branch: https://github.com/nerfstudio-project/nerfstudio/pull/3364 and data: https://drive.google.com/drive/folders/1LlWcbTCr2EO9g-VhNowhW1IRiMHbLzgZ?usp=sharing
Hardcode scene box values in
nerfstudio/data/dataparsers/nerfstudio_dataparser.py
and visualize it here https://github.com/nerfstudio-project/nerfstudio/pull/3363The tight box
The big box
Train instant-ngp with the following param
main difference: disable the scene contraction and use orientation method = align
Expected behavior Whenever the tight region of interest is used, the model fails to predict any rgb at all, while with the not so tight (simply 2x) the model quickly converges.
Not able to predict any rgb
Predicting fine
I can clearly see the wasted space in
viser
when use the not tight box. See example render with "white floaters" around https://github.com/user-attachments/assets/6f432305-2640-4fe6-a8d1-ed0da53dfd31I would love some pointers on why this behaviour could happen? What am I missing here?