Shin Joongchol, Paik Joonki
Department of Image, Chung-Ang University, Seoul 06974, Korea.
Sensors (Basel). 2021 Sep 15;21(18):6182. doi: 10.3390/s21186182.
Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze model estimation process requires very high computational complexity. To solve this problem by directly estimating the radiance of the haze images, we present a novel dehazing and verifying network (DVNet). In the dehazing procedure, we enhanced the clean images by using a correction network (CNet), which uses the ground truth to learn the haze network. Haze images are then restored through a haze network (HNet). Furthermore, a verifying method verifies the error of both CNet and HNet using a self-supervised learning method. Finally, the proposed complementary adversarial learning method can produce results more naturally. Note that the proposed discriminator and generators (HNet & CNet) can be learned via an unpaired dataset. Overall, the proposed DVNet can generate a better dehazed result than state-of-the-art approaches under various hazy conditions. Experimental results show that the DVNet outperforms state-of-the-art dehazing methods in most cases.
基于物理模型的去雾方法通常无法避免环境变量和诸如未采集到的照度、光晕和饱和度等不期望出现的伪影，因为难以准确估计照度、光传输和气辉的量。此外，雾度模型估计过程需要非常高的计算复杂度。为了通过直接估计雾度图像的辐射度来解决这个问题，我们提出了一种新颖的去雾与验证网络（DVNet）。在去雾过程中，我们使用一个校正网络（CNet）来增强清晰图像，该网络利用真实图像来学习雾度网络。然后通过雾度网络（HNet）恢复雾度图像。此外，一种验证方法使用自监督学习方法来验证CNet和HNet的误差。最后，所提出的互补对抗学习方法可以产生更自然的结果。请注意，所提出的判别器和生成器（HNet和CNet）可以通过未配对的数据集进行学习。总体而言，所提出的DVNet在各种雾度条件下都能产生比现有方法更好的去雾结果。实验结果表明，在大多数情况下，DVNet优于现有去雾方法。
