RSEND：基于Retinex的挤压与激励网络结合暗区检测用于高效低光图像增强
RSEND: Retinex-based Squeeze and Excitation Network with Dark Region Detection for Efficient Low Light Image Enhancement
AI总结：
提出单阶段Retinex框架RSEND，结合挤压与激励网络与暗区检测，高效增强低光图像，在多个数据集上PSNR提升0.44至4.2dB，并优于Transformer模型。
摘要：
在低光场景下拍摄的图像往往质量较差。以往基于CNN的深度学习方法常利用Retinex理论，但其中大多数在如LOL-v2等更复杂的数据集上表现不佳，同时消耗过多计算资源。此外，部分方法需要分阶段进行复杂的训练，使得整个过程更加耗时且繁琐。本文提出了一种更准确、简洁且单阶段的基于Retinex理论的框架RSEND。RSEND首先将低光图像分解为光照图和反射图，然后捕获光照图中的重要细节并进行光照增强。此步骤后，它细化增强后的灰度图像，并与反射图进行逐元素矩阵乘法。通过对上一步输出进行去噪，获得最终结果。在所有步骤中，RSEND利用挤压与激励网络以更好地捕获细节。全面的定量和定性实验表明，我们的高效Retinex模型显著优于其他基于CNN的模型，在不同数据集上PSNR提升范围从0.44 dB到4.2 dB，甚至在LOL-v2-real数据集上优于基于Transformer的模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
