南昌工程学院学报2025，Vol.44Issue(1)：81-90,10.
暗通道先验优化的生成对抗网络图像去雾算法
Generative adversarial network image dehazing algorithm with a dark channel priori optimization
摘要
Abstract
In order to solve the problems of dehazing image distortion,loss of detail and poor generalization of traditional im-age dehazing methods,this paper proposes a generative adversarial network image dehazing algorithm with a dark channel prior optimization.Firstly,a new model framework is designed,which generates an adversarial network through a priori opti-mization of dark channels,and the physical model is used to improve the convergence performance.Secondly,the residual auto-encoding is used to form a generator network,and the residual block is formed by jumping connections to retain the im-age detail information.Finally,the Markov discriminator was introduced to discriminate the dehazing image and fed back to the generator to further enhance the dehazing effect of the model.Experimental results show that the algorithm can effectively remove the fog layer in the foggy image,restore the image details well,ensure high visual quality,and perform well in a vari-ety of dehazing scenarios.关键词
图像去雾/生成对抗网络/暗通道先验/残差自编码/马尔可夫判别器Key words
image dehazing/generative adversarial networks/dark channel prior/residuals auto-encoded/Markov discrimina-tor分类
信息技术与安全科学引用本文复制引用
苏腾华,吕莉,樊棠怀,谢海华,刘宝宏..暗通道先验优化的生成对抗网络图像去雾算法[J].南昌工程学院学报,2025,44(1):81-90,10.基金项目
国家自然科学基金资助项目(62463021) （62463021）
