# GC-ART: Global Learnable Second-Order Rational Tone Curves for Illumination Robustness

Source: [GC-ART: Global Learnable Second-Order Rational Tone Curves for Illumination Robustness](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-12T05:00:04.827Z

Authors: Wei Huang, Joyce Huang

Published: 2026-05-08T06:34:22.000Z

## Abstract

We introduce GC-ART (Global Curve Adaptive Rational Tone-mapping), a lightweight differentiable pre-processing module for robust image classification. GC-ART predicts an endpoint-pinned rational tone curve from per-channel soft histograms using a 643-parameter MLP, then applies the curve pointwise before the classifier. The module is trained end-to-end with cross-entropy and a soft monotonicity penalty. On CIFAR-10 with a CIFAR-style ResNet-18, GC-ART matches clean accuracy with the unenhanced baseline and other learned enhancers, improves over the baseline on multiplicative darkening, and achieves the best learned-method result on contrast corruption (48.45% vs. 46.27% for the baseline and 47.13% for Zero-DCE++). These results suggest that histogram-conditioned rational curves can learn useful global tone corrections, including contrast-expanding behavior, while preserving edge locations by construction through pointwise mapping. GC-ART also uses substantially fewer FLOPs than convolutional learned enhancers at 32 x 32. The current hyperparameters are untuned, leaving room for systematic improvement.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 Contrast (severity-averaged) (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-contrast-severity-averaged-test.md>): Image Classification; CIFAR-10 Contrast (severity-averaged) (test); Accuracy: 48.45.

- [Image Classification on CIFAR-10 (Model Size and FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-size-and-flops.md>): Image Classification; CIFAR-10; Model Size (Params): 643.

- [Image Classification on CIFAR-10 Darken (severity-averaged) (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-darken-severity-averaged-test.md>): Image Classification; CIFAR-10 Darken (severity-averaged) (test); Accuracy: 87.24.

- [Image Classification on CIFAR-10-C Brightness (severity-averaged) (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-c-brightness-severity-averaged-test.md>): Image Classification; CIFAR-10 Brightness (severity-averaged) (test); Accuracy: 85.44.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.07329>)

[PDF](<https://arxiv.org/pdf/2605.07329.pdf>)