Single image haze removal using dark channel prior

By Kaiming He, Xiaoou Tang. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009

903 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/5585ecdf5d39c9f0ae0f12f89fab426f92baed68

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Underwater image dehazing using joint trilateral filter (2014, methodology): “[6] proposed the scene depth information-based dark channel prior dehazing algorithm by using matting Laplacian, which could be computational intensive.”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, methodology): “The proposed algorithm is more efficient than the state-ofthe-art image dehazing methods (Fattal 2008; He et al. 2011; Tarel et al. 2012; Meng et al. 2013; Zhu et al. 2015) in terms of run time.”
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation (2020, methodology): “For instance, markov random field [30,47,15] is often used to model the correlation among neighboring pixels, while dark channel prior [18] and total variation [31] are developed for dehazing and denoising respectively.”
Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception (2020, background): “s on restoring background illumination and lightness rendition. Another class of physics-based approaches uses an atmospheric dehazing model to estimate true transmission and ambient light in a scene [15,27]. Additional prior knowledge or statistical assumptions (e.g., haze-lines, dark channel prior”
Depth Transfer: Depth Extraction from Video Using Non-Parametric Sampling (2014, background): “The dark channel prior has also proven effective for estimating depth from images containing haze [13].”
Dehazing Using Color-Lines (2014, methodology): “Both these strategies require knowing the global atmospheric light vector A which can be estimated by various procedures, namely [Tan 2008; Fattal 2008; He et al. 2009; Tarel and Hauti`ere 2009].”
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network (2020, methodology): “…image, DehazeNet (Cai et al., 2016), MSCNN (Ren et al., 2016), AOD-Net (Li et al., 2017), DCP (He et al., 2009), GRM (Chen et al., 2016), N2V (Krull et al., 2019), DIP (He et al., 2009), DD (Heckel and Hand, 2019), DDIP (Irani, 2019), our method and the estimated transmission map are presented.”