基于行-列分离注意力的低光照图像/视频增强
Row-Column Separated Attention Based Low-Light Image/Video Enhancement
AI总结:
本文提出了一种行-列分离注意力模块(RCSA),用于改进U-Net结构以增强低光照图像和视频,通过减少参数和计算量来利用全局信息指导局部信息,同时提出两种时间损失函数以保持时间一致性。
摘要:
U-Net结构被广泛用于低光照图像/视频增强。增强的图像在没有适当全局信息指导的情况下,会导致局部噪声较大和细节丢失。注意力机制可以更好地关注和利用全局信息。然而,对图像的注意力可能会显著增加参数和计算量。我们提出了一种行-列分离注意力模块(RCSA),插入到改进的U-Net之后。RCSA模块的输入是特征图的行和列的均值和最大值,利用全局信息以较少的参数指导局部信息。我们提出两种时间损失函数,将该方法应用于低光照视频增强并保持时间一致性。在LOL、MIT Adobe FiveK图像和SDSD视频数据集上的广泛实验表明了我们方法的有效性。代码可在https://github.com/cq-dong/URCSA上公开获取。
英文摘要:
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.
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。