“…Part of these GAN variants mainly utilize multi-scale and attention mechanisme(e.g., channel attention, spatial attention) to efficiently extract hazy features, such as [44,43]. Besides, similar network architecture design ideas have also appeared in CNN-based dehazing networks [26,64,46,11,34,12,61]. Recently, visual transformers (ViT) is used to design different structures for improving dehazing performance [66,51,53,17].…”