UTCR-Dehaze: U-Net and transformer-based cycle-consistent generative adversarial network for unpaired remote sensing image dehazing

To address issues of feature loss and color differences in existing unpaired dehazing methods for Remote Sensing images, we propose a method based on a U-Net and Transformer-based Cycle-Consistent Generative Adversarial Network for unpaired remote sensing image dehazing (UTCR-Dehaze). In this model, considering that paired hazy images are difficult to obtain, a cycle-consistent generative adversarial network (CycleGAN) is used to achieve remote sensing image dehazing. Due to the multi-scale features of remote sensing images, U-Net is combined with Transformer as the generator of CycleGAN. The generator learns the relationship between low-frequency and high-frequency features of the image at multiple scales. The U-Net encoder–decoder processes the high-frequency features, and the transformer at the bottleneck of U-Net learns the low-frequency feature relationship to restore image details and structures. Secondly, to further improve the details and clarity of dehazed images, a Mixed Cascade Group Attention module (MCGA) is designed. MCGA captures the global information of the image through cascade group attention and focuses on local information through Dehaze input-dependent depthwise convolution, thus better learning image features. In addition, to reduce feature loss and color differences in dehazed images, a Cycle Perceptual Identity Consistency Loss is designed, which combines perceptual and identity losses to maintain the details of input images through cycle consistency. Numerous experiments on synthetic and real remote sensing datasets show that, compared with previous methods, this method not only removes haze more accurately but also preserves image details and colors to the greatest extent.