Rethinking Exposure Correction for Spatially Non-uniform Degradation

TL;DR

This paper introduces a novel exposure correction method tailored for spatially non-uniform degradation, utilizing a spatially adaptive architecture and an uncertainty-based loss to improve correction accuracy.

Contribution

It presents a new paradigm with a Spatial Signal Encoder and non-uniform loss, addressing limitations of existing uniform assumption-based methods.

Findings

Outperforms state-of-the-art methods in qualitative assessments.

Achieves superior quantitative correction metrics.

Effectively handles diverse real-world exposure errors.

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.