Low-light image enhancement has attracted great attention due to its capability in providing visible content and textures for video security and forensics. Unfortunately, conventional Retinex-based methods hardly pay attention to the complementarity of illumination and reflection. Inspired by the observation, we propose a new low-light image enhancement framework which relights the restored low-light image based on complementarity of illumination and reflection, named R²Net. The R²Net basically consists of three parts: image decomposition (Decom Net), reflection restoration (Restore Net), and illumination enhancement (Relight Net). In the Restore Net, we propose a mixed twofold attention (MTFA) module with linear complexity, introducing illumination information to model the mutual relationship between illumination and reflection. In MTFA, in order to capture richer information, we first map the inputs into different feature spaces, followed by combining them in different orders to obtain multiple sets of enhanced features. Accordingly, we design a differential enhanced fusion module (DEFM) to mix the multiple features. Ablation studies prove that the MTFA module significantly improves the performance of the restoration network. Finally, we propose a new illumination enhancement network (Relight Net), in which we introduce reflection to generate global information and define a luminance factor to tune the exposure level of output images, making our model more robust and flexible. Experiments show that our proposed method outperforms state-of-the-art methods in both quantitative comparison and visual perception.

低光图像增强由于其为视频安全和取证提供可见内容和纹理的能力而引起了极大的关注。不幸的是，传统的基于 Retinex 的方法几乎没有关注照明和反射的互补性。受观察的启发，我们提出了一种新的微光图像增强框架，该框架基于照明和反射的互补性重新点亮恢复的微光图像，称为 R ² Net。R ²Net基本上由三部分组成：图像分解（Decom Net）、反射恢复（Restore Net）和光照增强（Relight Net）。在Restore Net中，我们提出了一个具有线性复杂度的混合双重注意力（MTFA）模块，引入光照信息来模拟光照和反射之间的相互关系。在 MTFA 中，为了捕获更丰富的信息，我们首先将输入映射到不同的特征空间，然后以不同的顺序组合它们以获得多组增强特征。因此，我们设计了一个差分增强融合模块（DEFM）来混合多个特征。消融研究证明 MTFA 模块显着提高了恢复网络的性能。最后，我们提出了一种新的光照增强网络（Relight Net），其中我们引入反射来生成全局信息并定义亮度因子来调整输出图像的曝光水平，使我们的模型更加健壮和灵活。实验表明，我们提出的方法在定量比较和视觉感知方面都优于最先进的方法。