No abstract

Current learning-based dehazing ways simply rely on the paired synthetic datasets and physical models, which can hardly describe the complicated degradation for practical applications. These methods still struggle to achieve the haze removal, color distortion and detail restoration instantly, by ignoring the frequency characteristic differences and prior knowledge importance. To address these problems, we propose an unpaired stage-wise framework integrating Frequency-guided filtering and Progressive physics learning in an adversarial Dehazing network, called as FPD-Net. To be specific, a guided filter based on frequency information is employed to decompose the high and low frequency components for better feature extraction. We further merge the prior and physical knowledge to form progressive physics learning, which can produce pleasing haze-free outputs with visibility and reality. For better atmospheric light estimation, the variational auto-encoder and KL loss are included to represent the illumination message. Extensive experiments on both synthetic and real datasets prove that our designed FPD-Net achieves better performance visually and quantitatively than the comparing dehazing models.