改进生成对抗网络的图像去雾算法
Image Dehazing Algorithm with Improved Generative Adversarial Network
刘彦红 1杨秋翔1
作者信息
- 1. 中北大学软件学院,山西 太原 030051
- 折叠
摘要
雾霾天气下,可见光透过大气层时发生散射和吸收,导致图像质量变差、信息遮挡或丢失.基于此提出改进生成对抗网络(GAN)的图像去雾算法,该算法在生成器和鉴别器对抗中学习生成去雾图像.在生成器中,提出一种3行多列的多尺度融合注意力网络(Grid-G),引入通道注意力和像素注意力,分别从不同角度处理图像的厚雾区域和高频区域.在鉴别器中,引入图像中的高低频信息构建融合鉴别器(FD-F),将其作为额外先验判别图像的来源.在RESIDE数据集对合成数据和真实数据进行实验,实验结果表明本文算法在峰值信噪比和结构相似度等方面均优于其余对比算法,取得了更好的去雾效果,有效改善颜色失真等问题.
Abstract
In hazy weather,visible light scattering and absorption occur when passing through the atmosphere,resulting in poor image quality,information blocking or loss.Based on this,we propose an improved generative adversarial network(GAN)image dehazing algorithm,which learns to generate dehazed images in the generator and discriminator adversarial.In the generator,a three-row multi-column multi-scale fused attention network(Grid-G)is proposed to introduce channel attention and pixel atten-tion to process the thick haze region and high frequency region of the image from different angles,respectively.In the discrimina-tor,the high and low frequency information in the image is introduced to construct the fused discriminator(FD-F),which is used as a source of additional a priori discriminative images.Experiments on synthetic and real data in the RESIDE dataset show that the algorithm outperforms the rest of the comparison algorithms in terms of peak signal-to-noise ratio and structural similar-ity,achieves better dehazing effects,and effectively improves problems such as color distortion.
关键词
图像去雾/生成对抗网络/融合鉴别器Key words
image dehazing/generative adversarial network/fusion discriminator引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据