Single Image Haze Removal Using Dark Channel Prior

By Mohinder Malhotra. 2016

6,193 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

GAN Inversion: A Survey (2021, methodology): “It has been widely adopted in computer vision tasks, including MRF [196], [197], [198], dark channel prior [199] and total variation regularizer [200], which all model correlation among neighboring pixels via Gibbs distribution.”
Learning Affinity via Spatial Propagation Networks (2017, background): “For example, for low-level vision tasks such as image filtering, the affinity values should reveal the low-level coherence of color and texture [29, 28, 10, 9]; for mid to high-level vision tasks such as image matting and segmentation [16, 22], the affinity measure should reveal the semantic-level p”
DehazeNet: An End-to-End System for Single Image Haze Removal (2016, methodology): “Note that BReLU is equivalent to the boundary constraints used in traditional methods [9], [18].”
Gated Fusion Network for Single Image Dehazing (2018, methodology): “As shown, our method performs favor-(a) Hazy inputs (b) DCP [10] (c) BCCR [21] (d) NLD [3] (e) CAP [46] (f) MSCNN [28] (g) DehazeNet [4] (h) AOD-Net [14] (i) GFN ably against other competitors [3, 4, 14, 28] in this dataset.”
Cooperative Semantic Segmentation and Image Restoration in Adverse Environmental Conditions (2019, background): “, DCP [13], NLID [2] and MSCNN [33].”
An Underwater Image Enhancement Benchmark Dataset and Beyond (2019, background): “11, the proposed DUIENet effectively removes the haze on the underwater images and remits color casts, while the compared methods introduce unexpected colors (e.g., Fusion-based [29], GDCP [38], and Histogram Prior [42]) and artifacts (e.g., Fusion-based [29], Retinexbased [31], and Histogram Prior ”
Automatic Red-Channel underwater image restoration (2015, methodology): “However, one of the most popular methods up to date has been the Dark Channel Method, proposed in (17).”
Non-local Image Dehazing (2016, methodology): “Our method is compared to the method of [3] and an implementation of [5] by [3].”
MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, methodology): “They try to remove the inverted low-light image of haze by using the method proposed in [12] and then invert it again to get the ﬁnal result.”
Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light (2019, methodology): “We applied our RUIE benchmark to quantitatively and qualitatively evaluate eleven representative underwater image enhancement algorithms3 including original underwater enhancement methods MSRCR [1], CLAHE [2], Fusion [3], BP [5], UHP [7], NOM [8] and DPATN [18], and underwater extended application o”
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…”
Fast Underwater Image Enhancement for Improved Visual Perception (2019, background): “) are often utilized for global enhancements such as image deblurring, dehazing [21], etc.”
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors (2021, background): “9–11 are from authors of previous work [4–6].”
AOD-Net: All-in-One Dehazing Network (2017, methodology): “We evaluate it against the stateof-the-art methods on a few natural image examples, that were found to be highly challenging to dehaze [8, 7, 3].”