Have predicted depth as expected_depth so gradients can be computed #2852
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ArpegorPSGH
pushed a commit
to ArpegorPSGH/nerfstudio
that referenced
this pull request
Jun 22, 2024
…erfstudio-project#2852) Update depth_nerfacto.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In direct depth supervision methods, calling
depth_losswill not work unless we can compute gradients on the predicted depth. The predicted depth right now is a median and there are no gradients that can be computed. I have changed it to expected depth to allow direct depth supervision methods to work.