Generative adversarial networks with multi-scale and attention mechanisms for underwater image enhancement

Frontiers in Marine Science

Marine Science

Yanfei Jia¹  Ying Cui²  Tie Zhong³  Ziyang Wang³  Liquan Zhao³ 

[1] College of Electrical and Information Engineering, Beihua University, Jilin, China;Communication Network Operations Team of System Operations Department, Zhuhai Power Supply Bureau, Guangdong Power Grid Co., Ltd., Zhuhai, China;Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education (Northeast Electric Power University), Jilin, China;

关键词: underwater image enhancement;    generative adversarial network;    image quality;    image visual effect;    deep learning;   

DOI  :  10.3389/fmars.2023.1226024

 received in 2023-05-20, accepted in 2023-09-13,  发布年份 2023

来源: Frontiers

【 摘 要 】

The images captured underwater are usually degraded due to the effects of light absorption and scattering. Degraded underwater images exhibit color distortion, low contrast, and blurred details, which in turn reduce the accuracy of marine biological monitoring and underwater object detection. To address this issue, a generative adversarial network with multi-scale and an attention mechanism is proposed to improve the quality of underwater images. To extract more effective features within the generative network, several modules are introduced: a multi-scale dilated convolution module, a novel attention module, and a residual module. These modules are utilized to design a generative network with a U-shaped structure. The multi-scale dilated convolution module is designed to extract features at multiple scales and expand the receptive field to capture more global information. The attention module directs the network’s focus towards important features, thereby reducing the interference from redundant feature information. To improve the discriminative power of the adversarial network, a multi-scale discriminator is designed. It has two output feature maps with different scales. Additionally, an improved loss function for the generative adversarial network is proposed. This improvement involves incorporating the total variation loss into the traditional loss function. The performance of different methods for enhancing underwater images is evaluated using the EUVP dataset and UIEB dataset. The experimental results demonstrate that the enhanced underwater images exhibit better quality and visual effects compared to other methods.

【 授权许可】

Unknown   
Copyright © 2023 Wang, Zhao, Zhong, Jia and Cui