Transmission Estimation in Underwater Single Images

By Paulo L. J. Drews-Jr, Erickson R. Nascimento, Felipe Codevilla Moraes, Silvia Silva da Costa Botelho, Mario Fernando Montenegro Campos. 2013 IEEE International Conference on Computer Vision Workshops, 2013

731 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/91e6a0488b09ae18e32dd18bc29ee8d933cc77b6

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

Citations in the corpus

Generalization of the Dark Channel Prior for Single Image Restoration (2018, methodology): “7 shows comparisons of depth estimation based on the DCP [1], DCP variants [12], [13], [24], and our depth”
Color Balance and Fusion for Underwater Image Enhancement (2018, background): “To circumvent this issue, following the conclusions of previous underwater works [28], [29], we therefore primarily aim to compensate for the loss of the red channel.”
A Rapid Scene Depth Estimation Model Based on Underwater Light Attenuation Prior for Underwater Image Restoration (2018, positive): “Since the hazing effect of underwater images caused by light scattering and color change is similar to the fog effect in the air, He’s Dark Channel Prior (DCP) [3] and its variants [4], [8], [9] were used for depth estimation and restoration.”
Sea-Thru: A Method for Removing Water From Underwater Images (2019, methodology): “After a meticulous survey of these methods, authors in [7] found that DCP-based ones [21, 50] were not able to consistently correct colors, and others [3, 4, 5, 25] were designed to enhance images rather than achieve physically accurate corrections.”
Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, positive): “With considering the physical mechanism of underwater image degradation, Drews et al. [8], [10] proposed an adaptation of the DCP named underwater DCP (UDCP) to estimate the underwater transmission, and made use of blue and green color channels to enable a signiﬁcant improvement.”
Underwater Image Restoration Based on Image Blurriness and Light Absorption (2017, background): “In [12], [13], and [17], an underwater DCP based on only the green and blue channels (DCP gb ) was proposed to avoid this problem.”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, positive): “ICENet [26] and ICENetv2 [27] show that the two-branch network structure like BiSeNet [11] with a ﬁner spatial branch and a deep context semantic branch is very suitable to segment the river ice with scale diversity characteristic.”
WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images (2017, methodology): “Several methods have addressed range-dependent image dehazing by estimating depth through developed or statistical priors on attenuation effects [6], [7], [8].”
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (2018, methodology): “The transmission maps are shown only for the algorithms that estimate them for the color correction [14], [19], [24], [46] and ours.”
Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light (2019, methodology): “applied the modified underwater DCP only to the blue and green channels [9].”