Row-Column Separated Attention Based Low-Light Image/Video Enhancement
This work addresses the problem of low-light image/video enhancement for computer vision applications, offering an efficient attention mechanism that balances performance and computational cost.
The paper proposes a Row-Column Separated Attention module (RCSA) for low-light image/video enhancement, achieving improved performance with fewer parameters. On the LOL dataset, the method achieves a PSNR of 24.12 dB and SSIM of 0.882, outperforming prior methods.
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.