GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → JingyunLiang → SwinIR

JingyunLiang / SwinIR

Licence: Apache-2.0 License
SwinIR: Image Restoration Using Swin Transformer (official repository)

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

decompressiontransformersuper-resolutionimage-denoisingimage-restorationrestorationdenoisingimage-super-resolutionlow-level-visiondeblockingvision-transformerimage-deblockingcompression-artifact-reductionreal-world-image-super-resolutionlightweight-image-super-resolutionimage-sr

Projects that are alternatives of or similar to SwinIR

Awesome-low-level-vision-resources
A curated list of resources for Low-level Vision Tasks
Stars: ✭ 35 (-97.22%)
Mutual labels:  transformer, image-denoising, image-super-resolution
traiNNer
traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.
Stars: ✭ 130 (-89.68%)
Mutual labels:  super-resolution, image-restoration, denoising
CResMD
(ECCV 2020) Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
Stars: ✭ 92 (-92.7%)
Mutual labels:  image-restoration, denoising, low-level-vision
Restormer
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
Stars: ✭ 586 (-53.49%)
Mutual labels:  transformer, image-restoration, low-level-vision
HCFlow
Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)
Stars: ✭ 140 (-88.89%)
Mutual labels:  super-resolution, image-super-resolution, image-sr
towhee
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (-34.84%)
Mutual labels:  transformer, vision-transformer
image-classification
A collection of SOTA Image Classification Models in PyTorch
Stars: ✭ 70 (-94.44%)
Mutual labels:  transformer, vision-transformer
Super-Resolution-Meta-Attention-Networks
Open source single image super-resolution toolbox containing various functionality for training a diverse number of state-of-the-art super-resolution models. Also acts as the companion code for the IEEE signal processing letters paper titled 'Improving Super-Resolution Performance using Meta-Attention Layers’.
Stars: ✭ 17 (-98.65%)
Mutual labels:  super-resolution, image-restoration
LightFieldReconstruction
High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction
Stars: ✭ 50 (-96.03%)
Mutual labels:  super-resolution, image-restoration
semantic-segmentation
SOTA Semantic Segmentation Models in PyTorch
Stars: ✭ 464 (-63.17%)
Mutual labels:  transformer, vision-transformer
CWR
Code and dataset for Single Underwater Image Restoration by Contrastive Learning, IGARSS 2021, oral.
Stars: ✭ 43 (-96.59%)
Mutual labels:  image-restoration, low-level-vision
Trident-Dehazing-Network
NTIRE 2020 NonHomogeneous Dehazing Challenge (CVPR Workshop 2020) 1st Solution.
Stars: ✭ 42 (-96.67%)
Mutual labels:  super-resolution, low-level-vision
Uformer
[CVPR 2022] Official repository for the paper "Uformer: A General U-Shaped Transformer for Image Restoration".
Stars: ✭ 415 (-67.06%)
Mutual labels:  image-denoising, image-restoration
YOLOS
You Only Look at One Sequence (NeurIPS 2021)
Stars: ✭ 612 (-51.43%)
Mutual labels:  transformer, vision-transformer
visualization
a collection of visualization function
Stars: ✭ 189 (-85%)
Mutual labels:  transformer, vision-transformer
TransMorph Transformer for Medical Image Registration
TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)
Stars: ✭ 130 (-89.68%)
Mutual labels:  transformer, vision-transformer
LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+24.29%)
Mutual labels:  transformer, vision-transformer
Dehazing-PMHLD-Patch-Map-Based-Hybrid-Learning-DehazeNet-for-Single-Image-Haze-Removal-TIP-2020
This is the source code of PMHLD-Patch-Map-Based-Hybrid-Learning-DehazeNet-for-Single-Image-Haze-Removal which has been accepted by IEEE Transaction on Image Processing 2020.
Stars: ✭ 14 (-98.89%)
Mutual labels:  image-restoration, denoising
RCAN-tf
TensorFlow code for ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"
Stars: ✭ 25 (-98.02%)
Mutual labels:  super-resolution, image-restoration
DudeNet
Designing and Training of A Dual CNN for Image Denoising (Knowledge-based Systems, 2021)
Stars: ✭ 45 (-96.43%)
Mutual labels:  image-denoising, low-level-vision
View All Similar Projects ➔

SwinIR: Image Restoration Using Swin Transformer

Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, Radu Timofte

Computer Vision Lab, ETH Zurich

arXiv GitHub Stars download visitors google colab logo

This repository is the official PyTorch implementation of SwinIR: Image Restoration Using Shifted Window Transformer (arxiv, supp, pretrained models, visual results). SwinIR achieves state-of-the-art performance in

  • bicubic/lighweight/real-world image SR
  • grayscale/color image denoising
  • JPEG compression artifact reduction

🚀 🚀 🚀 News:

Real-World Image (x4) BSRGAN, ICCV2021 Real-ESRGAN SwinIR (ours) SwinIR-Large (ours)

* Please zoom in for comparison. Image 1 and Image 2 are randomly chosen from the web and from the RealSRSet+5images dataset, respectively.

  • Sep. 03, 2021: Add more detailed comparison between SwinIR and a representative CNN-based model RCAN (classical image SR, X4)
Method Training Set Training time
(8GeForceRTX2080Ti
batch=32, iter=500k)		 Y-PSNR/Y-SSIM
on Manga109		 Run time
(1GeForceRTX2080Ti,
on 256x256 LR image)*		 #Params #FLOPs Testing memory
RCAN DIV2K 1.6 days 31.22/0.9173 0.180s 15.6M 850.6G 593.1M
SwinIR DIV2K 1.8 days 31.67/0.9226 0.539s 11.9M 788.6G 986.8M

* We re-test the runtime when the GPU is idle. We refer to the evluation code here.

Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14~0.45dB, while the total number of parameters can be reduced by up to 67%.

Contents

  1. Training
  2. Testing
  3. Results
  4. Citation
  5. License and Acknowledgement

Training

Used training and testing sets can be downloaded as follows:

Task Training Set Testing Set Visual Results
classical/lightweight image SR DIV2K (800 training images) or DIV2K +Flickr2K (2650 images) Set5 + Set14 + BSD100 + Urban100 + Manga109 download all here
real-world image SR SwinIR-M (middle size): DIV2K (800 training images) +Flickr2K (2650 images) + OST (alternative link, 10324 images for sky,water,grass,mountain,building,plant,animal)
SwinIR-L (large size): DIV2K + Flickr2K + OST + WED(4744 images) + FFHQ (first 2000 images, face) + Manga109 (manga) + SCUT-CTW1500 (first 100 training images, texts)

*We use the pionnerring practical degradation model from BSRGAN, ICCV2021 GitHub Stars		 RealSRSet+5images here
color/grayscale image denoising DIV2K (800 training images) + Flickr2K (2650 images) + BSD500 (400 training&testing images) + WED(4744 images) grayscale: Set12 + BSD68 + Urban100
color: CBSD68 + Kodak24 + McMaster + Urban100 download all		 here
JPEG compression artifact reduction DIV2K (800 training images) + Flickr2K (2650 images) + BSD500 (400 training&testing images) + WED(4744 images) grayscale: Classic5 +LIVE1 download all here

The training code is at KAIR.

Testing (without preparing datasets)

For your convience, we provide some example datasets (~20Mb) in /testsets. If you just want codes, downloading models/network_swinir.py, utils/util_calculate_psnr_ssim.py and main_test_swinir.py is enough. Following commands will download pretrained models automatically and put them in model_zoo/swinir. All visual results of SwinIR can be downloaded here.

We also provide an online Colab demo for real-world image SR google colab logo for comparison with the first practical degradation model BSRGAN (ICCV2021) GitHub Stars and a recent model RealESRGAN. Try to test your own images on Colab!

# 001 Classical Image Super-Resolution (middle size)
# Note that --training_patch_size is just used to differentiate two different settings in Table 2 of the paper. Images are NOT tested patch by patch.
# (setting1: when model is trained on DIV2K and with training_patch_size=48)
python main_test_swinir.py --task classical_sr --scale 2 --training_patch_size 48 --model_path model_zoo/swinir/001_classicalSR_DIV2K_s48w8_SwinIR-M_x2.pth --folder_lq testsets/Set5/LR_bicubic/X2 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task classical_sr --scale 3 --training_patch_size 48 --model_path model_zoo/swinir/001_classicalSR_DIV2K_s48w8_SwinIR-M_x3.pth --folder_lq testsets/Set5/LR_bicubic/X3 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task classical_sr --scale 4 --training_patch_size 48 --model_path model_zoo/swinir/001_classicalSR_DIV2K_s48w8_SwinIR-M_x4.pth --folder_lq testsets/Set5/LR_bicubic/X4 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task classical_sr --scale 8 --training_patch_size 48 --model_path model_zoo/swinir/001_classicalSR_DIV2K_s48w8_SwinIR-M_x8.pth --folder_lq testsets/Set5/LR_bicubic/X8 --folder_gt testsets/Set5/HR

# (setting2: when model is trained on DIV2K+Flickr2K and with training_patch_size=64)
python main_test_swinir.py --task classical_sr --scale 2 --training_patch_size 64 --model_path model_zoo/swinir/001_classicalSR_DF2K_s64w8_SwinIR-M_x2.pth --folder_lq testsets/Set5/LR_bicubic/X2 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task classical_sr --scale 3 --training_patch_size 64 --model_path model_zoo/swinir/001_classicalSR_DF2K_s64w8_SwinIR-M_x3.pth --folder_lq testsets/Set5/LR_bicubic/X3 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task classical_sr --scale 4 --training_patch_size 64 --model_path model_zoo/swinir/001_classicalSR_DF2K_s64w8_SwinIR-M_x4.pth --folder_lq testsets/Set5/LR_bicubic/X4 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task classical_sr --scale 8 --training_patch_size 64 --model_path model_zoo/swinir/001_classicalSR_DF2K_s64w8_SwinIR-M_x8.pth --folder_lq testsets/Set5/LR_bicubic/X8 --folder_gt testsets/Set5/HR


# 002 Lightweight Image Super-Resolution (small size)
python main_test_swinir.py --task lightweight_sr --scale 2 --model_path model_zoo/swinir/002_lightweightSR_DIV2K_s64w8_SwinIR-S_x2.pth --folder_lq testsets/Set5/LR_bicubic/X2 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task lightweight_sr --scale 3 --model_path model_zoo/swinir/002_lightweightSR_DIV2K_s64w8_SwinIR-S_x3.pth --folder_lq testsets/Set5/LR_bicubic/X3 --folder_gt testsets/Set5/HR
python main_test_swinir.py --task lightweight_sr --scale 4 --model_path model_zoo/swinir/002_lightweightSR_DIV2K_s64w8_SwinIR-S_x4.pth --folder_lq testsets/Set5/LR_bicubic/X4 --folder_gt testsets/Set5/HR


# 003 Real-World Image Super-Resolution (use --tile 400 if you run out-of-memory)
# (middle size)
python main_test_swinir.py --task real_sr --scale 4 --model_path model_zoo/swinir/003_realSR_BSRGAN_DFO_s64w8_SwinIR-M_x4_GAN.pth --folder_lq testsets/RealSRSet+5images --tile

# (larger size + trained on more datasets)
python main_test_swinir.py --task real_sr --scale 4 --large_model --model_path model_zoo/swinir/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth --folder_lq testsets/RealSRSet+5images


# 004 Grayscale Image Deoising (middle size)
python main_test_swinir.py --task gray_dn --noise 15 --model_path model_zoo/swinir/004_grayDN_DFWB_s128w8_SwinIR-M_noise15.pth --folder_gt testsets/Set12
python main_test_swinir.py --task gray_dn --noise 25 --model_path model_zoo/swinir/004_grayDN_DFWB_s128w8_SwinIR-M_noise25.pth --folder_gt testsets/Set12
python main_test_swinir.py --task gray_dn --noise 50 --model_path model_zoo/swinir/004_grayDN_DFWB_s128w8_SwinIR-M_noise50.pth --folder_gt testsets/Set12


# 005 Color Image Deoising (middle size)
python main_test_swinir.py --task color_dn --noise 15 --model_path model_zoo/swinir/005_colorDN_DFWB_s128w8_SwinIR-M_noise15.pth --folder_gt testsets/McMaster
python main_test_swinir.py --task color_dn --noise 25 --model_path model_zoo/swinir/005_colorDN_DFWB_s128w8_SwinIR-M_noise25.pth --folder_gt testsets/McMaster
python main_test_swinir.py --task color_dn --noise 50 --model_path model_zoo/swinir/005_colorDN_DFWB_s128w8_SwinIR-M_noise50.pth --folder_gt testsets/McMaster


# 006 JPEG Compression Artifact Reduction (middle size, using window_size=7 because JPEG encoding uses 8x8 blocks)
python main_test_swinir.py --task jpeg_car --jpeg 10 --model_path model_zoo/swinir/006_CAR_DFWB_s126w7_SwinIR-M_jpeg10.pth --folder_gt testsets/classic5
python main_test_swinir.py --task jpeg_car --jpeg 20 --model_path model_zoo/swinir/006_CAR_DFWB_s126w7_SwinIR-M_jpeg20.pth --folder_gt testsets/classic5
python main_test_swinir.py --task jpeg_car --jpeg 30 --model_path model_zoo/swinir/006_CAR_DFWB_s126w7_SwinIR-M_jpeg30.pth --folder_gt testsets/classic5
python main_test_swinir.py --task jpeg_car --jpeg 40 --model_path model_zoo/swinir/006_CAR_DFWB_s126w7_SwinIR-M_jpeg40.pth --folder_gt testsets/classic5

Results

We achieved state-of-the-art performance on classical/lightweight/real-world image SR, grayscale/color image denoising and JPEG compression artifact reduction. Detailed results can be found in the paper. All visual results of SwinIR can be downloaded here.

Classical Image Super-Resolution (click me)

Lightweight Image Super-Resolution

Real-World Image Super-Resolution

Grayscale Image Deoising

Color Image Deoising

JPEG Compression Artifact Reduction

Citation

@inproceedings{liang2021swinir,
    title={SwinIR: Image Restoration Using Swin Transformer},
    author={Liang, Jingyun and Cao, Jiezhang and Sun, Guolei and Zhang, Kai and Van Gool, Luc and Timofte, Radu},
    booktitle={IEEE International Conference on Computer Vision Workshops},
    year={2021}
}

License and Acknowledgement

This project is released under the Apache 2.0 license. The codes are heavily based on Swin Transformer. We also refer to codes in KAIR and BasicSR. Please also follow their licenses. Thanks for their awesome works.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].