Model-based single image dehazing algorithms restore images with sharp edges and rich details at the expense of low PSNR values. Data-driven ones restore images with high PSNR values but with low contrast, and even some remaining haze. In this paper, a novel single image dehazing algorithm is introduced by fusing model-based and data-driven approaches. Both transmission map and atmospheric light are initialized by the model-based methods, and refined by deep learning approaches which form a neural augmentation. Haze-free images are restored by using the transmission map and atmospheric light. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images.
翻译:以模型为基础的单一图像脱色算法以降低PSNR低值为代价,以锐利边缘和丰富细节恢复图像,数据驱动图像以高PSNR值恢复图像,但对比度较低,甚至还存在一些烟雾。在本文中,通过采用基于模型和数据驱动的方法,采用了新的单一图像脱色算法。传输图和大气光均由基于模型的方法初始化,并通过形成神经增强的深层学习方法加以完善。无烟图像则通过使用传输图和大气光恢复。实验结果表明,拟议的算法可以去除真实世界和合成的烟雾图像中的烟雾。