fix: smooth Gaussian falloff for capped splat radii in compute renderer#8549
Merged
mvaligursky merged 1 commit intomainfrom Mar 24, 2026
Merged
fix: smooth Gaussian falloff for capped splat radii in compute renderer#8549mvaligursky merged 1 commit intomainfrom
mvaligursky merged 1 commit intomainfrom
Conversation
When a splat's projected extent exceeds the radius cap, rescale the covariance so the Gaussian reaches its cutoff at the capped boundary. Without this, splats close to the camera render as solid transparent rectangles with hard edges instead of smooth Gaussian falloff. This matches the quad renderer's implicit UV renormalization. Made-with: Cursor
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a splat's projected extent exceeds the radius cap (2 × min viewport dimension), the compute renderer rendered it as a solid transparent rectangle with hard edges — the Gaussian was still opaque at the boundary. The quad renderer didn't have this issue because its UV normalization implicitly rescales the falloff to fit the capped quad.
Changes: