Bayesian Defogging

By Ko Nishino, Louis Kratz, Stephen Lombardi. International Journal of Computer Vision, 2012

418 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f351a3d809348a470b2c70a3a1d09191f40a1f8c

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

Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, background): “On the other hand, restoring the visibility in hazy images based only on a single input RGB image is more challenging, being a mathematically ill-posed problem [5], [6], [7], [8], [9], [10], [11], [12].”
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding (2018, background): “During the past years, the community has made a tremendous progress on image dehazing (defogging) to increase the visibility of foggy images [24,40,56].”
Referenceless Prediction of Perceptual Fog Density and Perceptual Image Defogging (2015, methodology): “[16] suggested a Bayesian defogging model that jointly predicts the scene albedo and depths based on a factorial Markov random field.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, methodology): “In [92, 93], the authors use a factorial Markov random field that integrates the estimation of transmission and atmosphere light.”
Benchmarking Single-Image Dehazing and Beyond (2017, methodology): “Earlier works [22], [23] modeled the hazy image with a factorial Markov random field, where t (x) and A were two statistically independent latent layers.”
Non-local Image Dehazing (2016, methodology): “7 and 8 compare our results to state-of-the-art single image dehazing methods [1, 3, 4, 5, 12, 19].”
Domain Adaptation for Image Dehazing (2020, methodology): “Follow-up works have improved the efficiency and performance of the DCP method [30, 22, 17, 24, 34].”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, background): “Most dehazing methods use a variety of visual cues to capture deterministic and statistical properties of hazy images (Ancuti and Ancuti 2013; He et al. 2009, 2011; Ren and Cao 2017; Tan 2008; Tang et al. 2014; Zhu et al. 2015).”
Single Image Dehazing via Multi-scale Convolutional Neural Networks (2016, methodology): “Numerous dehazing methods based on the dark channel prior [1] have been developed [24,25,26,27].”
Visual Quality Enhancement Of Images Under Adverse Weather Conditions (2018, methodology): “Factorial MRF(Markov Random Field) based modeling [20] of the image have been used to increase image quality as well as to estimate the actual radiance of a scene better.”
Single Image Dehazing by Multi-Scale Fusion (2013, methodology): “as can be noticed by a closed inspection of figure 8 of [7], in figure 1 of [10] or in figure 6 of [14]).”
Gated Fusion Network for Single Image Dehazing (2018, background): “The DCP has been shown effective for image dehazing, and a number of methods improve [9] in terms of efficiency [35] or quality [24].”
Single Image Dehazing via Conditional Generative Adversarial Network (2018, background): “point out that the clear images and the corresponding depths are statistically independent and could be jointly estimated on the basis of priors [21].”
A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior (2015, methodology): “For fair comparison, the parameters used in the four popular dehazing methods are set to be optimal according to [29], [46], [49], and [50].”
DehazeNet: An End-to-End System for Single Image Haze Removal (2016, methodology): “[10] model the image with a factorial MRF to estimate the scene radiance more accurately; Meng et al.”