Dehazing Using Color-Lines

By Raanan Fattal. ACM Transactions on Graphics, 2014

1,130 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/c3d2534780e502d672f82c898f4fcedae3c78c8d

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

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].”
Gated Fusion Network for Single Image Dehazing (2018, methodology): “To further evaluate the proposed method, we use the real image dataset in Fattal [7] and compare with different stateof-the-art methods.”
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding (2018, background): “Extensive research has been conducted on image defogging (dehazing) to increase the visibility of foggy scenes [5,15,16,24,36,40,52].”
“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors (2018, background): “In image dehazing [6, 23, 18, 30, 8], the goal is to separate a hazy/foggy image into its underlying haze-free image and the obscuring haze/fog layers (airlight and transmission map).”
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].”
Color Balance and Fusion for Underwater Image Enhancement (2018, methodology): “[31], Fattal [32] and Gisbson et al.”
Fast End-to-End Trainable Guided Filter (2018, background): “dehaze the photos [5, 20, 14, 15], and even retouch the images for beautification [6].”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “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.”
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors (2021, methodology): “Fattal [9] introduced a color-line prior by the observation that pixels of small image patches typically exhibit a one-dimensional distribution in RGB color space.”
Semantic Foggy Scene Understanding with Synthetic Data (2017, neutral): “Depth and statistics of natural images are exploited as priors as well [6, 20, 21, 50].”
Image Dehazing Transformer with Transmission-Aware 3D Position Embedding (2022, background): “Subsequently, a variety of priors are proposed, such as color-line prior (CLP) [13] and haze-line prior (HLP) [3].”
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing (2019, methodology): “We further compare the proposed method against the state-of-the-arts on the real-world dataset [6].”
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (2020, background): “To solve these ill-posed problems, certain priors [15, 16, 23, 4] or careful algorithm designs are needed to make the problem well-posed.”
Domain Adaptation for Image Dehazing (2020, methodology): “Early prior-based methods try to estimate the transmission map by exploiting the statistical properties of clear images, such as dark channel prior [9] and color-line prior [8].”
O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images (2018, methodology): “(last column), and the results of several dehazing techniques [20, 28, 16, 8, 3, 7, 34], for the scenes 10, 19, and 41, respectively.”
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions (2021, background): “Adverse weather removal problems like deraining [16, 21,25,51,61,65,76], dehazing [1,2,10,22,42,69], desnowing [29,44,44,73] and rain drop removal [37,39,40,66] have been extensively explored in the literature.”
Non-local Image Dehazing (2016, methodology): “This is a local phenomena that does not always hold and indeed, in [3] care is taken to ensure only patches where the assumption holds are considered.”
NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images (2020, background): “Color lines [21] and haze-line [13] priors were built on the observation that the color distribution impacts the color channels distribution.”