Fig 1.
The imaging process using the atmospheric single scattering model, which ignores the multiple scattering of light in the atmosphere, but only considers the single scattering of light in the atmosphere.
Fig 2.
The imaging process using the atmospheric multiple scattering model.
Different from the atmospheric single scattering model, the atmospheric multiple scattering model takes into account the multiple scattering of light in the atmosphere and can describe the interaction between the reflected light from different sites.
Fig 3.
The dispersion spot generated by multiple scattering.
Due to the influence of multiple scattering, the original clear image will be blurred, and the dispersion spot will be formed in local area.
Fig 4.
The proposed unsupervised dehazing network.
In short, the unsupervised dehazing network consists of three unsupervised branches and a prior-based branch. The input hazy image is decomposed into four different layers by four branches, and then the four layers will be synthesized into hazy image according to the reconstructed atmospheric multiple scattering model.
Fig 5.
Clean image estimation branch, color attenuation energy loss is used for the constraint of network, the output of the network is a clean image with three-channel.
Fig 6.
Transmission map estimation branch, dark channel loss and total variation loss are used to constrain the network whose output is a single channel transmission map.
Fig 7.
Qualitative comparison of different methods on synthetic images.
From the left to the right column (i.e., Fig 7(a)–7(g)), the input hazy image, DCP [1], CAP [2], DehazNet [4], AOD-Net [5], GCAN [10], and our result).
Table 1.
The average results of SSIM and PSNR on the synthetic images.
Fig 8.
Quantitative comparison of different methods on real-world images.
From the left to the right column (i.e., Fig 8(a)–8(g)), the input hazy image, DCP [1], CAP [2], DehazNet [4], AOD-Net [5], GCAN [10], and our result).