Images captured under low-light scenarios often suffer from low quality. Previous CNN-based deep learning methods often involve using Retinex theory. Nevertheless, most of them cannot perform well in more complicated datasets like LOL-v2 while consuming too much computational resources. Besides, some of these methods require sophisticated training at different stages, making the procedure even more time-consuming and tedious. In this paper, we propose a more accurate, concise, and one-stage Retinex theory based framework, RSEND. RSEND first divides the low-light image into the illumination map and reflectance map, then captures the important details in the illumination map and performs light enhancement. After this step, it refines the enhanced gray-scale image and does element-wise matrix multiplication with the reflectance map. By denoising the output it has from the previous step, it obtains the final result. In all the steps, RSEND utilizes Squeeze and Excitation network to better capture the details. Comprehensive quantitative and qualitative experiments show that our Efficient Retinex model significantly outperforms other CNN-based models, achieving a PSNR improvement ranging from 0.44 dB to 4.2 dB in different datasets and even outperforms transformer-based models in the LOL-v2-real dataset.

在本文中，我们提出了基于RSEND的更为准确、简洁和单阶段的Retinex理论框架，该框架首先将低光照图像分解为光照图和反射图，然后捕捉光照图中重要的细节并进行光照增强，在此步骤之后，优化增强后的灰度图像并与反射图进行逐元素矩阵乘法运算，通过对前一步骤输出进行去噪，最终获得最终结果。全面的定量和定性实验表明，我们的高效Retinex模型明显优于其他基于CNN的模型，在不同数据集中的PSNR提升范围从0.44 dB到4.2 dB，甚至在LOL-v2-real数据集中优于基于Transformer的模型。

RSEND：基于Retinex和自适应低亮度区域检测的挤压与激励网络用于高效低光图像增强