提出行列分离注意力模块，提升暗光图像视频增强效果。
Row-Column Separated Attention Based Low-Light Image/Video Enhancement
- 用行列分离注意力提取全局信息，减少参数和计算量
- 在LOL、Adobe FiveK等数据集上显著提升细节保留能力
- 适合需要高效暗光增强的图像视频处理应用
U-Net结构广泛用于暗光图像/视频增强，但缺乏全局信息引导会导致局部噪声大、细节丢失。注意力机制虽能更好利用全局信息，却大幅增加参数与计算量。本文提出行-列分离注意力模块（RCSA），插入改进的U-Net中，其输入为特征图的行、列均值与最大值，以较少参数实现全局信息对局部信息的引导。同时设计两种时序损失函数，用于暗光视频增强并保持时间一致性。在LOL、MIT Adobe FiveK图像及SDSD视频数据集上的大量实验验证了方法的有效性。代码已开源：https://github.com/cq-dong/URCSA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。