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
Exploring the potential of channel interactions for image restoration
c-yn/ChaIR
•
•
Knowledge-Based Systems 2023
Image restoration aims to reconstruct a clear image from a degraded observation.
Encoder-minimal and Decoder-minimal Framework for Remote Sensing Image Dehazing
chdwyb/rshazenet
•
•
Haze obscures remote sensing images, hindering valuable information extraction.
Real-world image dehazing with improved joint enhancement and exposure fusion
The visual and quantitative comparisons between the proposed method and state-of-the-art dehazing methods show that the proposed method has better dehazing performance and has a 50% improvement in terms of the FADE metric compared to the closest result.
Image Restoration via Frequency Selection
c-yn/FSNet
•
•
IEEE Transactions on Pattern Analysis and Machine Intelligence 2023
Image restoration aims to reconstruct the latent sharp image from its corrupted counterpart.
Controlling Vision-Language Models for Multi-Task Image Restoration
In this paper, we present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a multi-task framework for image restoration.
Prompt-based test-time real image dehazing: a novel pipeline
We experimentally find that given a dehazing model trained on synthetic data, by fine-tuning the statistics (i. e., mean and standard deviation) of encoding features, PTTD is able to narrow the domain gap, boosting the performance of real image dehazing.
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.
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
fvl2020/iccv-2023-mb-taylorformer
•
•
ICCV 2023
To address this issue, we propose a new Transformer variant, which applies the Taylor expansion to approximate the softmax-attention and achieves linear computational complexity.
High-quality Image Dehazing with Diffusion Model
The latter stage exploits the strong generation ability of DDPM to compensate for the haze-induced huge information loss, by working in conjunction with the physical modelling.
Frequency Compensated Diffusion Model for Real-scene Dehazing
w-jilly/frequency-compensated-diffusion-model-pytorch
•
•
In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze.
