Model-Based Single Image Deep Dehazing
This addresses image quality issues in dehazing for computer vision applications, but it is incremental as it combines existing methods.
The paper tackles single image dehazing by fusing model-based and data-driven approaches, resulting in an algorithm that removes haze well from real-world and synthetic images.
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.