DefogNet: A Single-Image Dehazing Algorithm with Cyclic Structure and Cross-Layer Connections

• Published in: Complexity (New York, N.Y.) N.Y.), 2021, Vol.2021 (1)
• Main Authors: Chen, Suting, Fan, Wenhao, Peter, Shaw, Zhang, Chuang, Chen, Kui, Huang, Yong
• Format: Article
• Language: English
• Subjects: Algorithms; Atmospheric scattering; Color vision; Conversion; Convolution; Datasets; Feature extraction; Haze; Methods; Neural networks; Physics; Wavelet transforms
• ISSN: 1076-2787; 1099-0526
• DOI: 10.1155/2021/2352185

Inspired by the application of CycleGAN networks to the image style conversion problem Zhu et al. (2017), this paper proposes an end-to-end network, DefogNet, for solving the single-image dehazing problem, treating the image dehazing problem as a style conversion problem from a fogged image to a nonfogged image, without the need to estimate a priori information from an atmospheric scattering model. DefogNet improves on CycleGAN by adding a cross-layer connection structure in the generator to enhance the network’s multiscale feature extraction capability. The loss function was redesigned to add detail perception loss and color perception loss to improve the quality of texture information recovery and produce better fog-free images. In this paper, the novel Defog-SN algorithm is presented. This algorithm adds a spectral normalization layer to the discriminator’s convolution layer to make the discriminant network conform to a 1-Lipschitz continuum and further improve the model’s stability. In this study, the experimental process is completed based on the O-HAZE, I-HAZE, and RESIDE datasets. The dehazing results show that the method outperforms traditional methods in terms of PSNR and SSIM on synthetic datasets and Avegrad and Entropy on naturalistic images.