AI Rank
EN
← 开源
mv-lab

swin2sr

[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
695
Star
83
Fork
+0
本周
3
贡献者
创建于 2022-09-18 · 更新于 2026-09-26 · 今日第 14889 名
主要开发者
mv-labChoiuijin1125chenxwh

mv-lab/swin2sr 排名第 14,889，有 695 个星标。

同类别比较

mv-lab/swin2sr 排名第 14,889，此处有 8 个同类条目；soobinseo/Transformer-TTS 排名第 14,890。

同类别比较
名称排名指标
tkn-tub/ns3-gym14,870
语言:
C++
星标数:
697
分叉数:
221
简介:
ns3-gym - The Playground for Reinforcement Learning in Networking Research
vecxoz/vecstack14,871
语言:
Python
星标数:
697
分叉数:
79
简介:
Python package for stacking (machine learning technique)
HasnainRaz/Fast-SRGAN14,879
语言:
Python
星标数:
695
分叉数:
120
简介:
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
aleju/mario-ai14,883
语言:
Lua
星标数:
695
分叉数:
142
简介:
Playing Mario with Deep Reinforcement Learning
soobinseo/Transformer-TTS14,890
语言:
Python
星标数:
695
分叉数:
139
简介:
A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
flink-extended/dl-on-flink14,901
语言:
Java
星标数:
694
分叉数:
196
简介:
Deep Learning on Flink aims to integrate Flink and deep learning frameworks (e.g. TensorFlow, PyTorch, etc) to enable distributed deep learning training and inference on a Flink cluster.
khalil-research/PyEPO14,902
语言:
Jupyter Notebook
星标数:
694
分叉数:
90
简介:
A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming
KarhouTam/FL-bench14,908
语言:
Python
星标数:
693
分叉数:
116
简介:
Benchmark of federated learning. Dedicated to the community. 🤗
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
关键词Computer vision, Image production
星标数695
分叉数83
贡献者3
创建日期2022-09-18
更新日期2026-09-26
1 天星标数0
7 天星标数0
排名14,889
上次排名14,725
排名变化-164
7 天星标排名14,703
上次 7 天星标排名14,713
7 天星标排名变化10
总星标排名14,966
上次总星标排名14,938
总星标排名变化-28
国家Germany
README 摘录

Swin2SR @ ECCV 2022 AIM Workshop Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte Computer Vision Lab, CAIDAS, University of Würzburg | MegaStudyEdu, South Korea TLDR: Photorealistic super-resolution of compressed images using transformers / neural networks. **At AISP there is more work on image processing, low-level vision and computational photography. ** Try it out [01/2023] Swin2SR is integrated into **Stable Difussion webui by AUTOMATIC1111** [10/2022] Demos on

Kaggle, Collab and Huggingface Spaces 🤗 are ready! [09/2022] Ongoing website and multiple demos creation. Paper will be presented at the Advances in Image Manipulation (AIM) workshop, ECCV 2022, Tel Aviv. We provide the supplementary material, code, pretrained models and demos. Swin2SR represents a possible improvement of the famous SwinIR by Jingyun Liang (kudos for such an amazing contribution ✋). Our model achieves state-of-the-art performance in: classical, lighweight and real-world image super-resolution (SR) color JPEG compression

artifact reduction compressed input super-resolution: top solution at the "AIM 2022 Challenge on Super-Resolution of Compressed Image and Video" organized by Ren Yang and Radu Timofte Compression plays an important role on the efficient transmission and storage of images and videos through band-limited systems such as streaming services, virtual reality or videogames. However, compression unavoidably leads to artifacts and the loss of the original information, which may severely degrade the visual quality. For these reasons, quality enhancement

of compressed images has become a popular research topic. While most state-of-the-art image restoration methods are based on convolutional neural networks, other transformers-based methods such as SwinIR, show impressive performance on these tasks. In this paper, we explore the novel Swin Transformer V2, to improve SwinIR for image super-resolution, and in particular, the compressed input scenario. 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. We conduct experiments on three representative tasks: JPEG compression artifacts removal, image super-resolution (classical and lightweight), and compressed image super-resolution. Experimental results demonstrate that our method, Swin2SR, can improve the training convergence and performance of SwinIR, and is a top-5 solution at the "AIM 2022 Challenge on Super-Resolution of Compressed Image and Video". We follow the same training setup as SwinIR by Jingyun Liang. We

are working on KAIR integration 👀 More details about the training setup in our paper. Especially in the case of lightweight super-resolution, we noticed how our model convergence was approximately x2 faster using the same experimental setup as SwinIR. We provide the details in the paper Section 3 and 4. We use mainly the DIV2K Dataset and Flickr2K datasets for training, and for testing: RealSRSet, 5images/Classic5/Set5, Set14, BSD100, Urban100 and Manga109 🌎 **All visual results of Swin2SR can be

downloaded here**. We also provide links to download the original datasets. create a folder and put there the input images.

常见问题

记录了多少星标和分叉？

mv-lab/swin2sr 有 695 个星标和 83 个分叉。

仓库排名是多少？

mv-lab/swin2sr 排名第 14,889。

记录的语言和类别是什么？

mv-lab/swin2sr 有 695 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

mv-lab/swin2sr 与 soobinseo/Transformer-TTS 比较，后者排名第 14,890，有 695 个星标。

README

Swin2SR @ ECCV 2022 AIM Workshop

Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration

[ ](https://colab.research.google.com/drive/1paPrt62ydwLv2U2eZqfcFsePI4X4WRR1?usp=sharing) [ ](https://www.kaggle.com/code/jesucristo/super-resolution-demo-swin2sr-official/)

Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte

Computer Vision Lab, CAIDAS, University of Würzburg | MegaStudyEdu, South Korea

TLDR: Photorealistic super-resolution of compressed images using transformers / neural networks.

At AISP there is more work on image processing, low-level vision and computational photography.

News 🚀🚀

This is the official repository and PyTorch implementation of Swin2SR. We provide the supplementary material, code, pretrained models and demos. Swin2SR represents a possible improvement of the famous SwinIR by Jingyun Liang (kudos for such an amazing contribution ✋). Our model achieves state-of-the-art performance in:

Compression plays an important role on the efficient transmission and storage of images and videos through band-limited systems such as streaming services, virtual reality or videogames. However, compression unavoidably leads to artifacts and the loss of the original information, which may severely degrade the visual quality. For these reasons, quality enhancement of compressed images has become a popular research topic. While most state-of-the-art image restoration methods are based on convolutional neural networks, other transformers-based methods such as SwinIR, show impressive performance on these tasks. In this paper, we explore the novel Swin Transformer V2, to improve SwinIR for image super-resolution, and in particular, the compressed input scenario. 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. We conduct experiments on three representative tasks: JPEG compression artifacts removal, image super-resolution (classical and lightweight), and compressed image super-resolution. Experimental results demonstrate that our method, Swin2SR, can improve the training convergence and performance of SwinIR, and is a top-5 solution at the "AIM 2022 Challenge on Super-Resolution of Compressed Image and Video".

Contents

  1. Training
  2. Results
  3. Demos
  4. Testing
  5. Citation and Acknowledgement
  6. Contact

Training

The training code is at KAIR. We follow the same training setup as SwinIR by Jingyun Liang. We are working on KAIR integration 👀 More details about the training setup in our paper.

Why moving to Swin Transformer V2 ??

Especially in the case of lightweight super-resolution, we noticed how our model convergence was approximately x2 faster using the same experimental setup as SwinIR. We provide the details in the paper Section 3 and 4.2

Please check our demos ready to run 🚀

Results

We achieved state-of-the-art performance on classical, lightweight and real-world image Super-Resolution (SR), JPEG compression artifact reduction, and compressed input super-resolution. We use mainly the DIV2K Dataset and Flickr2K datasets for training, and for testing: RealSRSet, 5images/Classic5/Set5, Set14, BSD100, Urban100 and Manga109

🌎 All visual results of Swin2SR can be downloaded here. We also provide links to download the original datasets. More details in our paper.

Compressed inputs Swin2SR output

🌎 All the qualitative samples can be downloaded here

Basic inference setup

  1. create a folder inputs and put there the input images. The model expects low-quality and low-resolution JPEG compressed images.

  2. select --scale standard is 4, this means we will increase the resolution of the image x4 times. For example for a 1MP image (1000x1000) we will upscale it to near 4K (4000x4000).

  3. run our model using main_test_swin2sr.py and --save_img_only. The pre-trained models are included in our repo, you can download them from here or check the repo releases. It is important to select the proper --task, by default we do compressed input super-resolution compressed_s.

  4. we process the images in inputs/ and the outputs are stored in results/swin2sr_{TASK}_x{SCALE} where TASK and SCALE are the selected options. You can just navigate through results/

python main_test_swin2sr.py --task compressed_sr --scale 4 --training_patch_size 48 --model_path model_zoo/swin2sr/Swin2SR_CompressedSR_X4_48.pth  --folder_lq ./inputs --save_img_only

to reproduce results, calculate metrics and further evaluation, please check the following section Testing.

Demos

🔥 🚀 ✅ Kaggle kernel demo ready to run! easy to follow includes testing for multiple SR applications.

Clicke here to see how the Kaggle demo looks like

Super-Resolution Demo Swin2SR Official is also available in [Google Colab ](https://colab.research.google.com/drive/1paPrt62ydwLv2U2eZqfcFsePI4X4WRR1?usp=sharing)

We also have an interactive demo, no login required! in Huggingface Spaces 🤗 just click and upload images.

We are working on more interactive demos 👀 Contact us if you have ideas!

Testing

The original evaluation datasets can be downloaded from the following Kaggle Dataset

Classical image super-resolution (SR) Set5 + Set14 + BSD100 + Urban100 + Manga109 - download here

real-world image SR RealSRSet and 5images- download here

grayscale/color JPEG compression artifact reduction Classic5 +LIVE1 - download here

We follow the same evaluation setup as SwinIR by Jingyun Liang

🚀 You can check this evaluation process (and the followinf points) in our interactive kernel Official Swin2SR Demo Results

ClassicalSR

python main_test_swin2sr.py --task classical_sr --scale 2 --training_patch_size 64 --model_path model_zoo/swin2sr/Swin2SR_ClassicalSR_X2_64.pth --folder_lq testsets/Set5/LR_bicubic/X2 --folder_gt testsets/Set5/HR

python main_test_swin2sr.py --task classical_sr --scale 4 --training_patch_size 64 --model_path model_zoo/swin2sr/Swin2SR_ClassicalSR_X4_64.pth --folder_lq testsets/Set5/LR_bicubic/X4 --folder_gt testsets/Set5/HR

Lightweight

python main_test_swin2sr.py --task lightweight_sr --scale 2 --training_patch_size 64 --model_path model_zoo/swin2sr/Swin2SR_Lightweight_X2_64.pth --folder_lq testsets/Set5/LR_bicubic/X2 --folder_gt testsets/Set5/HR

RealSR

python main_test_swin2sr.py --task real_sr --scale 4 --model_path model_zoo/swin2sr/Swin2SR_RealworldSR_X4_64_BSRGAN_PSNR.pth --folder_lq testsets/RealSRSet+5images

CompressedSR

python main_test_swin2sr.py --task compressed_sr --scale 4 --training_patch_size 48 --model_path model_zoo/swin2sr/Swin2SR_CompressedSR_X4_48.pth --folder_gt path/to/DIV2K_Valid_HR --folder_lq /path/to/DIV2K_Valid_LR/Compressed_X4

JPEG Compression Artifact Reduction, Dynamic, GrayScale

python main_test_swin2sr.py --task jpeg_car --jpeg 10 --model_path model_zoo/swin2sr/Swin2SR_Jpeg_dynamic.pth --folder_gt /path/to/classic5
python main_test_swin2sr.py --task jpeg_car --jpeg 20 --model_path model_zoo/swin2sr/Swin2SR_Jpeg_dynamic.pth --folder_gt /path/to/classic5
python main_test_swin2sr.py --task jpeg_car --jpeg 30 --model_path model_zoo/swin2sr/Swin2SR_Jpeg_dynamic.pth --folder_gt /path/to/classic5
python main_test_swin2sr.py --task jpeg_car --jpeg 40 --model_path model_zoo/swin2sr/Swin2SR_Jpeg_dynamic.pth --folder_gt /path/to/classic5

Related Work

SwinIR: Image Restoration Using Swin Transformer by Liang et al, ICCVW 2021.

AISP: AI Image Signal Processing by Marcos Conde, Radu Timofte and collaborators, 2022.

AIM 2022 Challenge on Super-Resolution of Compressed Image and Video organized by Ren Yang.

Swin Transformer V2: Scaling Up Capacity and Resolution by Liu et al, CVPR 2022.

Citation and Acknowledgement

@inproceedings{conde2022swin2sr,
  title={{S}win2{SR}: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration},
  author={Conde, Marcos V and Choi, Ui-Jin and Burchi, Maxime and Timofte, Radu},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
  year={2022}
}

@article{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},
  journal={arXiv preprint arXiv:2108.10257},
  year={2021}
}

This project is released under the Apache 2.0 license. The codes are heavily based on Swin Transformer and SwinV2 Transformer by Ze Liu. We also refer to codes in KAIR, BasicSR and SwinIR. Please also follow their licenses. Thanks for their awesome works.

Contact

Marcos Conde (marcos.conde@uni-wuerzburg.de) and Ui-Jin Choi (choiuijin1125@gmail.com) are the contact persons. Please add in the email subject "swin2sr".

排名相邻
同类项目