Image Dehazing
114 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
Latest papers
TSNet:A Two-stage Network for Image Dehazing with Multi-scale Fusion and Adaptive Learning
Moreover, single-stage networks often result in many regions with artifacts and color distortion in output images.
WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazing
In this paper, we introduce WaveDH, a novel and compact ConvNet designed to address this efficiency gap in image dehazing.
A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint
There are two distinctions between nighttime and daytime haze.
Omni-Kernel Network for Image Restoration
c-yn/OKNet
•
•
Proceedings of the AAAI Conference on Artificial Intelligence 2024
Extensive experiments demonstrate that our network achieves state-of-the-art performance on 11 benchmark datasets for three representative image restoration tasks, including image dehazing, image desnowing, and image defocus deblurring.
FriendNet: Detection-Friendly Dehazing Network
In this paper, we raise an intriguing question: can the combination of image restoration and object detection enhance detection performance in adverse weather conditions?
Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
On the one hand, the difference perception between the depth maps of the dehazing result and the ideal image is proposed to promote the dehazing network to pay attention to the non-ideal areas of the dehazing.
Dual-domain strip attention for image restoration
c-yn/DSANet
•
•
Neural Networks 2024
In this paper, we develop a dual-domain strip attention mechanism for image restoration by enhancing representation learning, which consists of spatial and frequency strip attention units.
Physics Informed and Data Driven Simulation of Underwater Images via Residual Learning
anoynymreview/underwater_simulation
•
•
We propose a deep learning-based architecture to automatically simulate the underwater effects where only a dehazing-like image formation equation is known to the network, and the additional degradation due to the other unknown factors if inferred in a data-driven way.
U-shaped Vision Mamba for Single Image Dehazing
zzr-idam/uvm-net
•
•
Currently, Transformer is the most popular architecture for image dehazing, but due to its large computational complexity, its ability to handle long-range dependency is limited on resource-constrained devices.
Haze Removal via Regional Saturation-Value Translation and Soft Segmentation
The RSVT prior is developed based on two key observations regarding the relationship between hazy and haze-free points in the HSV color space.
