Repository navigation
Conversation
The affine color fit computes variance as E[x²]−E[x]² and clamps it to 1e-8. Nearly uniform but identifiable reference channels therefore lose their true slope, and singular reference channels are corrected toward zero rather than their mean.
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The affine color fit forms variance as E[x²] - E[x]² and clamps it to 1e-8. Nearly uniform but identifiable channels consequently lose their true slope; singular reference channels can be corrected toward zero instead of their mean.
Form covariance/variance from centered samples and handle singular channels with the reference mean. Preserve the public interface, output shape and final [0, 1] clipping.
Validation on Python 3.12.14 / PyTorch 2.8.0+cpu, with native full-package imports and the repository pytest configuration:
CUDA, full rendering/reconstruction suites, image-quality benchmarks and runtime/memory measurements were not run.