Title | ||
---|---|---|
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11263-019-01235-8 | International Journal of Computer Vision |
Keywords | Field | DocType |
Image dehazing, Image defogging, Convolutional neural network, Transmission map | Computer vision,Computer science,Convolutional neural network,Artificial intelligence,Prior probability,Artificial neural network | Journal |
Volume | Issue | ISSN |
128 | 1 | 0920-5691 |
Citations | PageRank | References |
21 | 0.60 | 15 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenqi Ren | 1 | 335 | 27.14 |
Jin-shan Pan | 2 | 567 | 30.84 |
Hua Zhang | 3 | 328 | 13.64 |
Xiaochun Cao | 4 | 1986 | 131.55 |
Yang Ming-Hsuan | 5 | 15303 | 620.69 |