With the continuous advancement of imaging devices, the prevalence of Ultra-High-Definition (UHD) images is rising. Although many image restoration methods have achieved promising results, they are not directly applicable to UHD images on devices with limited computational resources due to the inherently high computational complexity of UHD images. In this paper, we focus on the task of low-light image enhancement (LLIE) and propose a novel LLIE method called MixNet, which is designed explicitly for UHD images. To capture the long-range dependency of features without introducing excessive computational complexity, we present the Global Feature Modulation Layer (GFML). GFML associates features from different views by permuting the feature maps, enabling efficient modeling of long-range dependency. In addition, we also design the Local Feature Modulation Layer (LFML) and Feed-forward Layer (FFL) to capture local features and transform features into a compact representation. This way, our MixNet achieves effective LLIE with few model parameters and low computational complexity. We conducted extensive experiments on both synthetic and real-world datasets, and the comprehensive results demonstrate that our proposed method surpasses the performance of current state-of-the-art methods. The code will be available at \url{https://github.com/zzr-idam/MixNet}.

翻译：随着成像设备的持续进步，超高清（UHD）图像的普及度日益提升。尽管许多图像恢复方法已取得显著成果，但由于UHD图像本身的高计算复杂度，这些方法在计算资源受限的设备上无法直接应用于UHD图像。本文聚焦于低光照图像增强（LLIE）任务，提出一种名为MixNet的新型LLIE方法，该方法专门为UHD图像设计。为在不引入过高计算复杂度的情况下捕获特征的远距离依赖关系，我们提出了全局特征调制层（GFML）。GFML通过置换特征图将不同视图的特征相关联，从而高效建模远距离依赖关系。此外，我们还设计了局部特征调制层（LFML）和前馈层（FFL），用于捕获局部特征并将特征转换为紧凑表示。通过这种方式，我们的MixNet以较少的模型参数和较低的计算复杂度实现了高效的LLIE。我们在合成数据集和真实世界数据集上进行了大量实验，综合结果表明，我们所提出的方法超越了当前最先进方法的性能。代码将发布于\url{https://github.com/zzr-idam/MixNet}。