Yu Wenshuo, Zhao Liquan, Zhong Tie
Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education, Northeast Electric Power University, Jilin 132012, China.
Entropy (Basel). 2023 Jun 13;25(6):932. doi: 10.3390/e25060932.
Low-light image enhancement aims to improve the perceptual quality of images captured under low-light conditions. This paper proposes a novel generative adversarial network to enhance low-light image quality. Firstly, it designs a generator consisting of residual modules with hybrid attention modules and parallel dilated convolution modules. The residual module is designed to prevent gradient explosion during training and to avoid feature information loss. The hybrid attention module is designed to make the network pay more attention to useful features. A parallel dilated convolution module is designed to increase the receptive field and capture multi-scale information. Additionally, a skip connection is utilized to fuse shallow features with deep features to extract more effective features. Secondly, a discriminator is designed to improve the discrimination ability. Finally, an improved loss function is proposed by incorporating pixel loss to effectively recover detailed information. The proposed method demonstrates superior performance in enhancing low-light images compared to seven other methods.
低光图像增强旨在提高在低光条件下拍摄图像的感知质量。本文提出了一种新颖的生成对抗网络来提高低光图像质量。首先，它设计了一个由带有混合注意力模块和并行扩张卷积模块的残差模块组成的生成器。残差模块旨在防止训练期间梯度爆炸并避免特征信息丢失。混合注意力模块旨在使网络更加关注有用特征。并行扩张卷积模块旨在增加感受野并捕获多尺度信息。此外，利用跳跃连接将浅层特征与深层特征融合以提取更有效的特征。其次，设计了一个鉴别器以提高鉴别能力。最后，通过纳入像素损失提出了一种改进的损失函数，以有效恢复详细信息。与其他七种方法相比，所提出的方法在增强低光图像方面表现出卓越的性能。
