Add support for sparse depth maps #1373
Merged
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
* sparse depth maps * pr comments * unified loss * minor * lint
chris838
pushed a commit
to chris838/nerfstudio
that referenced
this pull request
Apr 22, 2023
Add support for sparse depth maps (nerfstudio-project#2) * sparse depth maps * pr comments * unified loss * minor * lint
Open
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Outdated suggestions cannot be applied.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.
Background
In nerfstudio, the losses for depth don't support sparse depth maps.
Description
Modified
ds_nerf_depth_loss,urban_radiance_field_depth_lossinlosses.py.Modified the way of computing
depth_msein eval.Fixed typo
Depht->Depth.Verification
Train
depth-nerfactowith theReplicaDataset using only two views with sparse depth supervision (randomly masking out 90% of the depth map). left: groundtruth sparse depth map. right: predicted dense depth map. Results below are generated usingds_nerf_depth_loss.