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
Most implemented papers
Lower Bound on Transmission Using Non-Linear Bounding Function in Single Image Dehazing
The accuracy and effectiveness of SID depends on accurate value of transmission and atmospheric light.
Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
diptamath/Nonhomogeneous_Image_Dehazing
•
•
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2020
Recently, CNN based end-to-end deep learning methods achieve superiority in Image Dehazing but they tend to fail drastically in Non-homogeneous dehazing.
Distilling Image Dehazing With Heterogeneous Task Imitation
dmcv-ecnu/MindSpore_ModelZoo
•
•
CVPR 2020
The student network imitates the task of image reconstruction in the teacher network.
Blind Video Temporal Consistency via Deep Video Prior
ChenyangLEI/deep-video-prior
•
•
NeurIPS 2020
Extensive quantitative and perceptual experiments show that our approach obtains superior performance than state-of-the-art methods on blind video temporal consistency.
Improving Image Restoration by Revisiting Global Information Aggregation
Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.
Image Dehazing Transformer With Transmission-Aware 3D Position Embedding
Li-Chongyi/Dehamer
•
•
CVPR 2022
Though Transformer has occupied various computer vision tasks, directly leveraging Transformer for image dehazing is challenging: 1) it tends to result in ambiguous and coarse details that are undesired for image reconstruction; 2) previous position embedding of Transformer is provided in logic or spatial position order that neglects the variational haze densities, which results in the sub-optimal dehazing performance.
Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
AOD-Net: All-In-One Dehazing Network
kritiksoman/GIMP-ML
•
•
ICCV 2017
This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net).
Benchmarking Single Image Dehazing and Beyond
inyong37/Vision
•
•
We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE).
Single Image Dehazing Using Color Ellipsoid Prior
The proposed method constructs color ellipsoids that are statistically fitted to haze pixel clusters in RGB space and then calculates the transmission values through color ellipsoid geometry.
