提出可自适应光照引导的Transformer模型，提升暗光图像非均匀光照还原效果。
SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement
- 用动态积分图建模空间变化光照，实现精准光照估计
- 在五个标准数据集上超越当前最佳方法，尤其在背光与阴影场景表现优异
- 适合需要高保真暗光增强的应用，如夜视、医疗成像
基于Transformer的暗光增强方法在全局光照恢复方面取得进展，但在背光、阴影等非均匀光照场景中仍存在过曝或亮度恢复不足的问题。为此，我们提出空间自适应光照引导变压器（SAIGFormer），通过动态积分图表示建模空间变化的光照，并设计新型空间自适应积分光照估计器（SAI²E）。此外，引入光照引导多头自注意力机制（IG-MSA），利用光照信息校准与亮度相关的特征，实现视觉愉悦的光照增强。在五个标准暗光数据集及跨域基准LOL-Blur上的大量实验表明，SAIGFormer在定量和定性指标上均显著优于现有方法。尤其在非均匀光照增强任务中表现突出，且在多个数据集上展现出强泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。