Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges

• Published in: International journal of computer vision Vol. 128; no. 1; pp. 240 - 259
• Main Authors: Ren, Wenqi, Pan, Jinshan, Zhang, Hua, Cao, Xiaochun, Yang, Ming-Hsuan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2020; Springer; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Artificial neural networks; Computer Imaging; Computer Science; Datasets; Image Processing and Computer Vision; Image processing systems; Image quality; Image transmission; Mapping; Neural networks; Pattern Recognition; Pattern Recognition and Graphics; Vision; Transmission map; Image defogging; Image dehazing; Convolutional neural network
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-019-01235-8

Single image dehazing has been a challenging problem which aims to recover clear images from hazy ones. The performance of existing image dehazing methods is limited by hand-designed features and priors. In this paper, we propose a multi-scale deep neural network for single image dehazing by learning the mapping between hazy images and their transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines dehazed results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. In addition, we propose a holistic edge guided network to refine edges of the estimated transmission map. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.