U-Net structure is widely used for low-light image/video enhancement. The enhanced images result in areas with large local noise and loss of more details without proper guidance for global information. Attention mechanisms can better focus on and use global information. However, attention to images could significantly increase the number of parameters and computations. We propose a Row-Column Separated Attention module (RCSA) inserted after an improved U-Net. The RCSA module's input is the mean and maximum of the row and column of the feature map, which utilizes global information to guide local information with fewer parameters. We propose two temporal loss functions to apply the method to low-light video enhancement and maintain temporal consistency. Extensive experiments on the LOL, MIT Adobe FiveK image, and SDSD video datasets demonstrate the effectiveness of our approach. The code is publicly available at https://github.com/cq-dong/URCSA.

翻译：U-Net结构被广泛用于低光照图像/视频增强。在没有全局信息适当引导的情况下，增强后的图像会出现局部噪声较大、细节丢失较多的问题。注意力机制能更好地聚焦并利用全局信息。然而，对图像应用注意力机制会显著增加参数量和计算量。我们提出了一种行列分离注意力模块，将其嵌入改进后的U-Net结构之后。该模块以特征图行、列的均值与最大值为输入，能以较少的参数量利用全局信息引导局部信息。我们还提出了两种时序损失函数，以将本方法应用于低光照视频增强并保持时序一致性。在LOL、MIT Adobe FiveK图像数据集及SDSD视频数据集上的大量实验证明了本方法的有效性。代码已公开于https://github.com/cq-dong/URCSA。