fix gradient missing during densify&prune #828
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
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Outdated suggestions cannot be applied.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 a solved issue(#562) about the initial position of the cloned gaussians, it is mentioned that the new gaussians' gradient will be zero while the old gaussians' gradient will remain so that they will get seperated in the next step.
But I notice that after we called function
densify_and_prune, the gradient of gaussian parameter becomes None, which indicates the next step is not able to seperate the new and the old gaussians and this contradicts with the original paper.I made a tiny change to the implementation of densify & prune process and now the new gaussians' gradient will be exactly zero while others remain the same, thus seperate the two.