论文标题
双尺度的单图像通过神经增强进行除去
Dual-Scale Single Image Dehazing Via Neural Augmentation
论文作者
论文摘要
基于模型的单图像去悬算算法还恢复了带有尖锐边缘的无雾图像，而真实世界的朦胧图像的丰富细节则以低psnr和SSIM值的牺牲来恢复合成朦胧的图像。数据驱动的图像恢复了合成朦胧图像的较高PSNR和SSIM值的无雾图像，但对比度低，甚至对于现实世界中的朦胧图像而言，甚至剩下的雾度。在本文中，通过组合基于模型和数据驱动的方法来引入一种新型的单图像飞行算法。传输图和大气光都是通过基于模型的方法估算的，然后通过基于双尺度生成对抗网络（GAN）的方法进行完善。所得算法形成了一种神经增强，在相应的数据驱动方法可能不会收敛的同时，该算法会很快收敛。通过使用估计的传输图和大气光以及KoschmiederLaw来恢复无雾图像。实验结果表明，所提出的算法可以从现实世界和合成朦胧的图像中井除雾霾。
Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free images with high PSNR and SSIM values for synthetic hazy images but with low contrast, and even some remaining haze for real world hazy images. In this paper, a novel single image dehazing algorithm is introduced by combining model-based and data-driven approaches. Both transmission map and atmospheric light are first estimated by the model-based methods, and then refined by dual-scale generative adversarial networks (GANs) based approaches. The resultant algorithm forms a neural augmentation which converges very fast while the corresponding data-driven approach might not converge. Haze-free images are restored by using the estimated transmission map and atmospheric light as well as the Koschmiederlaw. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images.
