5-Degradation Blind All-in-One Image Restoration
6 papers with code • 1 benchmarks • 0 datasets
Blind All-in-One Image Restoration aims to remove various degradations from an input image without prior knowledge of the degradation type or severity. In this task, we include 5 of the most common image restoration tasks with five degradations: rain, haze, noise, blur, and low-light conditions. This task focuses on five common image restoration tasks, each addressing a specific degradation: rain , haze, noise, blur, and low-light conditions. For training, we utilize the following datasets: Rain200L for deraining, RESIDE for dehazing, WED and BSD400 for denoising with a noise level of σ=25, GoPro for deblurring, and LoLv1 for low-light enhancement. For evaluation, we employ: Rain100L for deraining, SOTS (outdoor) for dehazing, BSD68 for denoising with σ=25, GoPro for deblurring, and LoLv1 for low-light enhancement. The performance of the models is assessed by reporting the average PSNR across all five evaluation datasets, reflecting the overall capability of the model to handle diverse degradations.
Benchmarks
These leaderboards are used to track progress in 5-Degradation Blind All-in-One Image Restoration
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Most implemented papers
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration
xl-tang3/DA-RCOT
•
•
More crucially, we design the transport map for restoration as a two-pass DA-RCOT map, in which the transport residual is computed in the first pass and then encoded as multi-scale residual embeddings to condition the second-pass restoration.
All-in-One Image Restoration for Unknown Corruption
xlearning-scu/2022-cvpr-airnet
•
•
CVPR 2022
In this paper, we study a challenging problem in image restoration, namely, how to develop an all-in-one method that could recover images from a variety of unknown corruption types and levels.
Ingredient-Oriented Multi-Degradation Learning for Image Restoration
JingHao99/IDR-Ingredients-oriented-Degradation-Reformulation
•
•
CVPR 2023
Learning to leverage the relationship among diverse image restoration tasks is quite beneficial for unraveling the intrinsic ingredients behind the degradation.
Restore Anything Model via Efficient Degradation Adaptation
Amazingren/AnyIR
•
•
With the proliferation of mobile devices, the need for an efficient model to restore any degraded image has become increasingly significant and impactful.
HAIR: Hypernetworks-based All-in-One Image Restoration
toummHus/HAIR
•
•
To alleviate this issue, we propose HAIR, a Hypernetworks-based All-in-One Image Restoration plug-and-play method that generates parameters based on the input image and thus makes the model to adapt to specific degradation dynamically.
Adaptive Blind All-in-One Image Restoration
Blind all-in-one image restoration models aim to recover a high-quality image from an input degraded with unknown distortions.
