Single Image Dehazing via Deep Learning-based Image Restoration
Chia‐Hung Yeh, Chih-Hsiang Huang, Li‐Wei Kang, Min-Hui Lin · 2018
Images/videos captured from outdoor visual devices are usually degraded by turbid media, such as haze, smoke, fog, rain, and snow. Haze is the most common one in outdoor scenes due to the atmosphere conditions. This paper presents a deep learning-based architecture for single image dehazing via image restoration. instead of learning an end-to-end mapping between each pair of hazy image and its corresponding haze-free one adopted by most existing approaches, we propose to transform the problem into the restoration of the image base component. By first decomposing the hazy image into the base and the detail components, haze removal can be achieved by learning a CNN (convolutional neural network) only for mapping between hazy and haze-free base components, while the detail component can be further enhanced. As a result, the final dehazed image is obtained by integrating the haze-removed base and the enhanced detail image components. Experimental results have demonstrated good efficacy of the proposed method, compared with state-of-the-art results.