A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior

By Qingsong Zhu, Jiaming Mai, Ling Shao. IEEE Transactions on Image Processing, 2015

2,250 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/042e12e44ad99e55f509b2128d9a5bea2212e0c7

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

Domain Adaptation for Image Dehazing (2020, background): “Representative works in this regard include [29, 9, 39, 8, 2].”
Gated Fusion Network for Single Image Dehazing (2018, methodology): “PSNR/SSIM DCP [10] BCCR [21] NLD [3] CAP [46] MSCNN [28] DehazeNet [4] AOD-Net [14] GFN (G) GFN (G+D)”
Single Image Dehazing via Multi-scale Convolutional Neural Networks (2016, methodology): “The proposed algorithm is more efficient than the state-of-the-art image dehazing methods [1,11,23,25,27] in terms of run time.”
Enhanced Pix2pix Dehazing Network (2019, background): “[25] recovered depth information via color attenuation prior.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, background): “locally constant constraints and decorrelation of the transmission [87], dark channel prior [9], color attenuation prior [88], nonlocal prior [89].”
Generalization of the Dark Channel Prior for Single Image Restoration (2018, methodology): “methods described in [4], [5], [17], and [19].”
DehazeNet: An End-to-End System for Single Image Haze Removal (2016, methodology): “4(c), F1 is similar to the maximum contrast [7] (see Equation (6)); when W1 includes all-pass filters and opposite filters, F1 is similar to the maximum and minimum feature maps, which are atomic operations of the color space transformation from RGB to HSV, then the color attenuation [18] (see Equat”
Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing (2018, methodology): “By outperforming the state-of-the-art methods [8, 10, 16, 24, 38] according to PSNR metric, our model achieves the second best result.”
DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention (2023, background): “The widely known priors include dark channel prior (DCP) [19], [20], non-local prior (NLP) [21], color attenuation prior (CAP) [22], etc. Specifically, He et al. [19], [20] propose DCP, leveraging a crucial observation that most local patches in haze-free outdoor images contain pixels with very low…”
Densely Connected Pyramid Dehazing Network (2018, methodology): “All the re-sults are compared with ﬁve state-of-the-art methods: He et al. (CVPR’09) [13], Zhu et al (TIP’15) [57], Ren et al. [33] (ECCV’16), Berman et al. [3, 4] (CVPR’16 and ICCP’17) and Li et al. [24] (ICCV’17).”
Fast and memory efficient de-hazing technique for real-time computer vision applications (2020, background): “They are Zhu et al. [6], Tarel et al. [14], He et al. [4] and Tripathi et al. [15] in terms of MSE, PSNR, Average Time cost, Average Contrast of the output image and visibility analysis (percentage of haze improvement).”
Gated Context Aggregation Network for Image Dehazing and Deraining (2018, methodology): “From these visual results, we can easily observe that DCP [17] and CAP [46] will make the brightness of the dehazed results relatively dark, which is because of their underlying prior assumptions.”
Visual Quality Enhancement Of Images Under Adverse Weather Conditions (2018, background): “Zhu et al. [6] learns a supervised linear model to estimate the depth map of a hazy image.”
Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, background): “…of Meng et al. [13] is based on a regularization strategy and reﬁnes the boundaries of the rough transmission estimated by DCP. Similarly, Zhu et al. [14] extends DCP by considering a color attenuation prior under the assumption that the depth can be estimated from pixel saturation and intensity.”
Single Image Dehazing via Conditional Generative Adversarial Network (2018, background): “In recent years, we have witnessed significant advances in image dehazing mainly due to using hand-crafted features to estimate transmission maps and atmospheric lights [1, 3, 4, 10, 11, 19, 20, 22, 40].”