Enable SparseNerf depth ranking loss to be used with GT/Sensor depth #2312
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Outdated suggestions cannot be applied.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.
PR #2066 adds a very nice ranking-based loss that can be used with non-metric depth. The ranking loss can also be used with metric depth, and seems to provide smoother results on the replica dataset (image below).
This PR is a minimal set of changes that allows the ranking loss to be used with depth read from disk (usually GT/sensor depth).