Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images

@article{Ancuti2019DenseHazeAB,
  title={Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images},
  author={Codruta Orniana Ancuti and Cosmin Ancuti and Mateu Sbert and Radu Timofte},
  journal={2019 IEEE International Conference on Image Processing (ICIP)},
  year={2019},
  pages={1014-1018}
}
  • C. Ancuti, C. Ancuti, R. Timofte
  • Published 5 April 2019
  • Computer Science
  • 2019 IEEE International Conference on Image Processing (ICIP)
Single image dehazing is an ill-posed problem that has recently drawn important attention. [] Key Result Not surprisingly, our study reveals that the existing dehazing techniques perform poorly for dense homogeneous hazy scenes and that there is still much room for improvement.

Figures and Tables from this paper

NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images
TLDR
This work presents an objective assessment of several state- of-the-art single image dehazing methods that were evaluated using NH-HAZE dataset, a non-homogeneous realistic dataset with pairs of real hazy and corresponding haze-free images.
Varicolored Image De-Hazing
TLDR
Visual results on a set of real-world hazy images captured in different weather conditions demonstrate the effectiveness of the proposed approach for varicolored image de-hazing.
Supplementary Materials for “Contrastive Learning for Compact Single Image Dehazing”
For synthetic scenes, we select the ITS and SOTS indoor in RESIDE [3], which consist of 13,990 and 500 samples, respectively. Their sizes are the same, i.e. 620×460. For real-world scenes, we adopt
Learning to Restore Hazy Video: A New Real-World Dataset and A New Method
TLDR
This work proposes the first REal-world VIdeo DEhazing (REVIDE) dataset which can be used for the supervised learning of the video dehazing algorithms and develops a Confidence Guided and Improved Deformable Network (CG-IDN) for videoDehazing.
Uneven Image Dehazing by Heterogeneous Twin Network
TLDR
An image-to-image architecture to handle the uneven image dehazing is proposed, in which a heterogeneous twin network (HT-Net) with two parallel sub-networks are constructed to establish the high dimensional nonlinear mapping model between the hazy and clean images.
Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
TLDR
This paper proposes a novel density-variational learning framework to improve the robustness of the image dehzing model as-sisted by a variety of negative hazy images, to better deal with various complex hazy scenarios.
Multi-Scale Adaptive Dehazing Network
TLDR
An adaptive distillation network is developed to solve the dehaze problem with non-uniform haze, which does not rely on the physical scattering model and outperforms the state-of-the-arts in both quantitative and qualitative evaluations.
Residual Spatial and Channel Attention Networks for Single Image Dehazing
TLDR
An end-to-end trainable densely connected residual spatial and channel attention network based on the conditional generative adversarial framework to directly restore a haze-free image from an input hazy image, without explicitly estimation of any atmospheric scattering parameters is proposed.
Haziness Degree Evaluator: A Knowledge-Driven Approach for Haze Density Estimation
TLDR
This paper proposes a model that is known as the haziness degree evaluator to predict haze density from a single image without reference to a corresponding haze-free image, an existing georeferenced digital terrain model, or training on a significant amount of data.
...
...

References

SHOWING 1-10 OF 42 REFERENCES
O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images
TLDR
The first outdoor scenes database composed of pairs of real hazy and corresponding haze-free images is introduced, and is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000.
D-HAZY: A dataset to evaluate quantitatively dehazing algorithms
TLDR
A dataset that contains 1400+ pairs of images with ground truth reference images and hazy images of the same scene, built on the Middelbury and NYU Depth datasets that provide images of various scenes and their corresponding depth maps is introduced.
NTIRE 2018 Challenge on Image Dehazing: Methods and Results
TLDR
This paper reviews the first challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results and gauges the state-of-the-art in imageDehazing.
Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing
TLDR
It is shown that the dark-channel feature is the most informative one for this task, which confirms the observation of He et al.
AIPNet: Image-to-Image Single Image Dehazing With Atmospheric Illumination Prior
TLDR
This paper proposes a straightforward but remarkable prior—atmospheric illumination prior that tries to maintain the intrinsic color of hazy scene and enhance its visual contrast, and applies the multiscale convolutional networks that can automatically identify hazy regions and restore deficient texture information.
DehazeNet: An End-to-End System for Single Image Haze Removal
TLDR
This paper proposes a trainable end-to-end system called DehazeNet, for medium transmission estimation, which takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model.
Multi-scale Single Image Dehazing Using Perceptual Pyramid Deep Network
TLDR
This work presents a multi-scale image dehazing method using Perceptual Pyramid Deep Network based on the recently popular dense blocks and residual blocks and is ranked among top-3 methods in terms of quantitative performance in the recently conducted NTIRE2018-Dehazing challenge.
A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior
TLDR
A simple but powerful color attenuation prior for haze removal from a single input hazy image is proposed and outperforms state-of-the-art haze removal algorithms in terms of both efficiency and the dehazing effect.
Learning a Patch Quality Comparator for Single Image Dehazing
TLDR
Quantitative and qualitative evaluations show that the proposed dehazing method achieves good results in most of the cases, and are, on an average, comparable with the state-of-the-art methods.
HazeRD: An outdoor scene dataset and benchmark for single image dehazing
TLDR
A new dataset, HazeRD, is proposed for benchmarking dehazing algorithms under more realistic haze conditions, which allows for more realistic simulation of haze with parameters that are physically realistic and justified by scattering theory.
...
...