# Rethinking Exposure Correction for Spatially Non-uniform Degradation

Source: [Rethinking Exposure Correction for Spatially Non-uniform Degradation](<https://www.sota2.com/research/paper/69d48fd77d0172140ec74680>)

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

Data updated: 2026-04-08T05:00:12.103Z

Authors: Ao Li, Jiawei Sun, Le Dong, Zhenyu Wang, Weisheng Dong

Published: 2026-04-05T14:41:59.000Z

## Abstract

Real-world exposure correction is fundamentally challenged by spatially non-uniform degradations, where diverse exposure errors frequently coexist within a single image. However, existing exposure correction methods are still largely developed under a predominantly uniform assumption. Architecturally, they typically rely on globally aggregated modulation signals that capture only the overall exposure trend. From the optimization perspective, conventional reconstruction losses are usually derived under a shared global scale, thus overlooking the spatially varying correction demands across regions. To address these limitations, we propose a new exposure correction paradigm explicitly designed for spatial non-uniformity. Specifically, we introduce a Spatial Signal Encoder to predict spatially adaptive modulation weights, which are used to guide multiple look-up tables for image transformation, together with an HSL-based compensation module for improved color fidelity. Beyond the architectural design, we propose an uncertainty-inspired non-uniform loss that dynamically allocates the optimization focus based on local restoration uncertainties, better matching the heterogeneous nature of real-world exposure errors. Extensive experiments demonstrate that our method achieves superior qualitative and quantitative performance compared with state-of-the-art methods. Code is available at https://github.com/FALALAS/rethinkingEC.

## 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.

- [Exposure Correction on MSEC Average](<https://www.sota2.com/research/sota/exposure-correction-on-msec-average.md>): Exposure Correction; MSEC Average; PSNR: 23.72.

- [Exposure Correction on SICE (Average)](<https://www.sota2.com/research/sota/exposure-correction-on-sice-average.md>): Exposure Correction; SICE (Average); PSNR: 22.67.

- [Exposure Correction on MSEC (Under)](<https://www.sota2.com/research/sota/exposure-correction-on-msec-under.md>): Exposure Correction; MSEC (Under); PSNR: 23.64.

- [Exposure Correction on MSEC (Over)](<https://www.sota2.com/research/sota/exposure-correction-on-msec-over.md>): Exposure Correction; MSEC (Over); PSNR: 23.83.

- [Exposure Correction on SICE Under](<https://www.sota2.com/research/sota/exposure-correction-on-sice-under.md>): Exposure Correction; SICE Under; PSNR: 23.49.

- [Exposure Correction on SICE (Over)](<https://www.sota2.com/research/sota/exposure-correction-on-sice-over.md>): Exposure Correction; SICE (Over); PSNR: 21.85.

- [Exposure Correction on REED Under](<https://www.sota2.com/research/sota/exposure-correction-on-reed-under.md>): Exposure Correction; REED Under; PSNR: 26.91.

- [Exposure Correction on REED Over](<https://www.sota2.com/research/sota/exposure-correction-on-reed-over.md>): Exposure Correction; REED Over; PSNR: 24.53.

- [Exposure Correction on REED Average](<https://www.sota2.com/research/sota/exposure-correction-on-reed-average.md>): Exposure Correction; REED Average; PSNR: 25.68.

- [Exposure Correction on LCDP](<https://www.sota2.com/research/sota/exposure-correction-on-lcdp.md>): Exposure Correction; LCDP; PSNR: 24.41.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.04136>)

[PDF](<https://arxiv.org/pdf/2604.04136.pdf>)
