-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
Fix depth-nerfacto edge cases #2939
Conversation
…udio-project/nerfstudio into ethan/fix_depth_nerfacto_sampling
nerfstudio/data/pixel_samplers.py
Outdated
|
||
if "mask" in batch: | ||
num_rays_in_batch = num_rays_per_batch // num_images | ||
if num_rays_in_batch % 2 != 0: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this could be moved above if statement and 293-294 deleted right?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
other than small fix, lgtm
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
* fixes pixel sampling * reverting indexing change * adressing PR change --------- Co-authored-by: Justin Kerr <justin.g.kerr@gmail.com>
Depth nerfacto doesn't work unless num_rays_in_batch is divisible by 2. Also, the depth images are in a list and not just a batch tensor, so I think the changes I made are needed.