Image Dehazing
113 papers with code • 11 benchmarks • 16 datasets
( Image credit: Densely Connected Pyramid Dehazing Network )
Benchmarks
These leaderboards are used to track progress in Image Dehazing
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
KITTI
O-HAZE
RESIDE
DENSE
I-HAZE
NH-HAZE
Haze4k
D-HAZY
Most implemented papers
Densely Connected Pyramid Dehazing Network
hezhangsprinter/DCPDN
•
•
CVPR 2018
We propose a new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazing all together.
PAD-Net: A Perception-Aided Single Image Dehazing Network
In this work, we investigate the possibility of replacing the $\ell_2$ loss with perceptually derived loss functions (SSIM, MS-SSIM, etc.)
Deep-Energy: Unsupervised Training of Deep Neural Networks
The success of deep learning has been due, in no small part, to the availability of large annotated datasets.
Improved Techniques for Learning to Dehaze and Beyond: A Collective Study
Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e. g., object detection) of hazy images.
Progressive Feature Fusion Network for Realistic Image Dehazing
MKFMIKU/PFFNet
•
•
Most of them follow a classic atmospheric scattering model which is an elegant simplified physical model based on the assumption of single-scattering and homogeneous atmospheric medium.
Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset
The attenuation depends both on the water body and the 3D structure of the scene, making color restoration difficult.
Gated Context Aggregation Network for Image Dehazing and Deraining
cddlyf/GCANet
•
•
Image dehazing aims to recover the uncorrupted content from a hazy image.
"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors
yossigandelsman/DoubleDIP
•
•
Computer Vision Foundation 2018
It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image.
Image Dehazing via Joint Estimation of Transmittance Map and Environmental Illumination
pranoy-panda/ICAPR2017_Dehazing
•
•
Image dehazing methods try to recover haze-free image by removing the effect of haze from a given input image.
Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP.
