SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement

TL;DR

SAIGFormer is a novel Transformer-based framework that effectively restores non-uniform illumination in low-light images by modeling spatially-varying light and guiding feature calibration, outperforming existing methods.

Contribution

The paper introduces a spatially-adaptive illumination modeling and a new attention mechanism for low-light enhancement, addressing non-uniform lighting challenges.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Excels in non-uniform illumination scenarios.

Demonstrates strong cross-domain generalization.

Abstract

Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination. However, they still struggle with non-uniform lighting scenarios, such as backlit and shadow, appearing as over-exposure or inadequate brightness restoration. To address this challenge, we present a Spatially-Adaptive Illumination-Guided Transformer (SAIGFormer) framework that enables accurate illumination restoration. Specifically, we propose a dynamic integral image representation to model the spatially-varying illumination, and further construct a novel Spatially-Adaptive Integral Illumination Estimator ($\text{SAI}^2\text{E}$). Moreover, we introduce an Illumination-Guided Multi-head Self-Attention (IG-MSA) mechanism, which leverages the illumination to calibrate the lightness-relevant features toward visual-pleased illumination enhancement. Extensive experiments on five standard low-light datasets and a cross-domain benchmark (LOL-Blur) demonstrate that our SAIGFormer significantly outperforms state-of-the-art methods in both quantitative and qualitative metrics. In particular, our method achieves superior performance in non-uniform illumination enhancement while exhibiting strong generalization capabilities across multiple datasets. Code is available at https://github.com/LHTcode/SAIGFormer.git.