JPEG Artifact Correction
12 papers with code • 26 benchmarks • 5 datasets
Correction of visual artifacts caused by JPEG compression, these artifacts are usually grouped into three types: blocking, blurring, and ringing. They are caused by quantization and removal of high frequency DCT coefficients.
Benchmarks
These leaderboards are used to track progress in JPEG Artifact Correction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
DIV2K
BSDS500
LIVE (Public-Domain Subjective Image Quality Database)
Classic5
ICB
Most implemented papers
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
cszn/DnCNN
•
•
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
titu1994/Image-Super-Resolution
•
•
In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
Multi-level Wavelet-CNN for Image Restoration
With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork.
Compression Artifacts Reduction by a Deep Convolutional Network
ryanxingql/powerqe
•
•
ICCV 2015
Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring.
Residual Dense Network for Image Restoration
yulunzhang/RDN
•
•
We fully exploit the hierarchical features from all the convolutional layers.
MemNet: A Persistent Memory Network for Image Restoration
We apply MemNet to three image restoration tasks, i. e., image denosing, super-resolution and JPEG deblocking.
Towards Flexible Blind JPEG Artifacts Removal
jiaxi-jiang/fbcnn
•
•
ICCV 2021
Training a single deep blind model to handle different quality factors for JPEG image artifacts removal has been attracting considerable attention due to its convenience for practical usage.
Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration
mv-lab/swin2sr
•
•
Using this method we can tackle the major issues in training transformer vision models, such as training instability, resolution gaps between pre-training and fine-tuning, and hunger on data.
Quantization Guided JPEG Artifact Correction
Queuecumber/quantization-guided-ac
•
•
ECCV 2020
The JPEG image compression algorithm is the most popular method of image compression because of its ability for large compression ratios.
Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal
VDIGPKU/QGCN
•
•
Our proposed network is a single model approach that can be trained for handling a wide range of quality factors while consistently delivering superior or comparable image artifacts removal performance.
