Enhanced Pix2pix Dehazing Network

In this paper we reduce the image dehazing problem to an image-to-image translationproblem, and propose Enhanced Pix2pix Dehazing Network (EPDN), which generates a haze-free image without relying on the physical scattering model. EPDN is embedded by a generative adversarial network, which isfollowed by a well-designed enhancer Inspiredby visualperception global-first[5] theory,the discriminatorguides the generatorto create apseudo realistic image on a coarse scale, while the enhancerfollowing the generator is required to produce a realistic dehazing image on the fine scale. The enhancer contains two enhancing blocks based on the receptivefield model, which reinforces the dehazing effect in both color and details. The embedded GAN is jointly trainedwith the enhancer Extensive experiment results on synthetic datasets and real-world datasets show that the proposed EPDN is superior to the state-ofthe-art methods in terms of PSNR, SSIM, PI, and subjective visual effect.