Underwater Image Enhancement Based on Multi-scale Adversarial Network

In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.

基于生成对抗网络的深海图像增强算法

在复杂的深海环境中提高图像的质量和可视化效果对水下科学研究和工程应用具有重要意义。针对深海特殊环境导致深海数据集稀缺,以及深海图像存在的色彩失真、对比度低等问题本文构建了一个成对的深海图像数据集DSIEB,并在此基础上提出了一种结合DC注意力和MSDR多尺度密集残差的生成对抗网络DM-GAN算法。首先,在网络跳跃连接部分构建DC双重通道注意力机制,用于加强通道间联系,提取图像细节纹理特征。其次,在生成器结构中嵌入MSDR多尺度密集残差块,提高对局部信息的关注和特征重用能力。最后,重构新的损失函数,引入平滑保真度SF损失,从多个角度引导网络学习原始图像到目标图像的映射。通过在自建数据集DSIEB上进行实验验证,并与7种先进水下图像增强算法进行对比实验,实验结果表明本文所提算法具有更强的泛化能力,适应于多样性的深海图像。