Bugfix: ShN incorrectly reshaping when NaN present #2044
Conversation
This file contains hidden or 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
Signed-off-by: Joe Nordling <[email protected]>
|
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Outdated suggestions cannot be applied.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.
Currently if there is an NaN or Inf value when saving out the Gaussian Splat to a .ply file using
GaussianSplat3d::savePly, thedispatchGaussianNanInfMaskwill remove it before writing the file. However, the spherical harmonics are still reshaped based off of the premasked tensor shape, which leads to a crash due to mismatched tensor shapes.This PR adds a test case to check for this error in the future and a fix to reshape the tensor to the correct shape.