Single image defogging method based on multi-scale self-attention generative adversarial network

The invention discloses a single image defogging method based on a multi-scale self-attention generative adversarial network, and the method comprises the steps: carrying out the training of a generative adversarial network model constructed through the downsampling of an image twice through a training set formed by the normalization of the image, and obtaining a trained generative adversarial network model; and optimizing the defogging result by using a loss function in the training process, and finally inputting the foggy image into the generative adversarial network model to obtain a defogged image. According to the single image defogging method provided by the invention, the problem of poor defogged image quality in the prior art is solved. 本发明公开的基于多尺度自注意生成对抗网络的单幅图像去雾方法，通过将图像归化成的训练集对将图像进行两次下采样构建的生成对抗网络模型进行训练，得到训练后的生成对抗网络模型，训练过程中对去雾结果用损失函数进行优化，最后将有雾图像输入到生成对抗网络模型中，得到去雾图像。本发明提供的单幅图像去雾方法，解决了现有技术中去雾图像质量差的问题。