Row-Column Separated Attention Based Low-Light Image/Video Enhancement

TL;DR

This paper introduces a novel Row-Column Separated Attention module integrated into U-Net for low-light image and video enhancement, effectively utilizing global information with fewer parameters and maintaining temporal consistency.

Contribution

It proposes a new attention module that efficiently captures global information and applies temporal loss functions for improved low-light video enhancement.

Findings

Effective enhancement on LOL, MIT Adobe FiveK, and SDSD datasets.

Fewer parameters compared to traditional attention mechanisms.

Maintains temporal consistency in video enhancement.

Abstract

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.