Histogram sort for uncompressed gsplat #7596
Merged
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
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR implements the remaining work for leveraging histogram bit allocation for uncompressed scenes, improving the sorting of gaussians by adapting to their distribution.
- Updates the splat sorting branch to use a 4-float chunk representation instead of 6 floats.
- Refactors the bounding sphere calculation and bounds updating logic from chunk data and vertex centers.
willeastcott
approved these changes
Apr 24, 2025
slimbuck
added a commit
that referenced
this pull request
Apr 25, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Fixes #7585
This PR is a follow up to #7472. It implements the remaining work required to leverage histogram bit allocation for uncompressed scenes.
Using a histogram to allocate bits helps when sorting gaussians in scenes with especially wildly distributed gaussians (i.e. scenes with dense clumps of gaussians together with very huge, sparsely distributed far away gaussians).
This scene provided by Simon Bethke went from:
To:
In order to use the histogram we must just calculate a bounding sphere for every 256 gaussians (under the assumption the gaussians were previously ordered) at load time.