Initial results in underwater single image dehazing

By Nicholas Carlevaris-Bianco, Anush Mohan, Ryan M. Eustice. OCEANS 2010 MTS/IEEE SEATTLE, 2010

482 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6554d59867907742259235d2647f37d71a592f19

How researchers see this paper

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

Citations in the corpus

Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior (2016, unknown): “…include Single Image Dehazing (SID) method [10], Dark Channel Prior (DCP) method [11], Chromatism-based (CB) underwater image dehazing method [17], Wavelength Compensation and Dehazing (WCID) underwater image enhancement method [18], Histogram Equalization (HE) method, and Probability-based…”
A Revised Underwater Image Formation Model (2018, methodology): “Current underwater color correction methods [5, 8, 9, 12, 13, 26, 27, 31, 36, 40] rely on a commonly used image formation model first derived for haze [3, 4, 14, 17, 39].”
Underwater Image Enhancement by Wavelength Compensation and Dehazing (2012, methodology): “The colors processed by the WCID proposed, by dark-channel dehazing [8], by chromatism-based dehazing [24], and histogram equalization algorithms [11] are compared with the ground-truth ones taken above water, as shown in Figs.”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, unknown): “Especially, the size of river ice ranges from a few pixels to thousands of pixels in an image.”
Generalization of the Dark Channel Prior for Single Image Restoration (2018, methodology): “Underwater test images from [13], [16], [38] and Google Images.”
Automatic Red-Channel underwater image restoration (2015, methodology): “With any of the three possibilities, the hypothesis of the theorem is verified.”
Emerging From Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer (2017, methodology): “ion methods [17], [18]. The hardware solutions [3]–[6] have shown the effectiveness, but these solutions are not applicable to dynamic acquisition. Most of single underwater image restoration methods [7]–[13] are inspired by the outdoor dehazing strategies [19]–[22]. For underwater image color corre”
An Underwater Image Enhancement Benchmark Dataset and Beyond (2019, background): “[41] proposed a prior that exploits the difference in attenuation among three”
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (2018, background): “Carlevaris-Bianco et al. [3] assume a color-independent transmission, and propose a variant of DCP based on the difference between the maximum of the red channel and the maximum of the blue and green channels in each patch.”
Sea-Thru: A Method for Removing Water From Underwater Images (2019, methodology): “This was done to enable recovery from single images in haze [8, 26, 33, 57] and later used also for underwater recovery [17, 19, 21, 44, 49].”
WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images (2017, unknown): “Several methods have addressed range-dependent image dehazing by estimating depth through developed or statistical priors on attenuation effects [10]–[12].”
Automated annotation of coral reef survey images (2012, background): “, the red colors are attenuated as a function of depth [4].”
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”
Color Balance and Fusion for Underwater Image Enhancement (2018, methodology): “In contrast, applying DCP on our white balanced image version (last column), results in comparable and even better estimates compared with the specialized underwater techniques corresponding to UDCP [49], MDCP [50], BP [51] and Lu et al.”
U-Shape Transformer for Underwater Image Enhancement (2021, methodology): “[37] used the attenuation difference prior between the three color channels in RGB color space to predict the transmission characteristics of the underwater scene, which feasibility is basically due to red light generally decays faster than green and blue light.”
Underwater Image Restoration Based on Image Blurriness and Light Absorption (2017, methodology): “This concept was ﬁrst proposed in [9], where D mip was used to estimate the TM, rather than the depth directly.”