English | 简体中文

:rocket: We add BasicSR-Examples, which provides guidance and templates of using BasicSR as a python package. :rocket:

:loudspeaker: 技术交流QQ群：320960100   入群答案：互帮互助共同进步

:compass: 入群二维码 (QQ、微信)    入群指南 (腾讯文档)

---

Google Colab: GitHub Link | Google Drive Link
:m: Model Zoo: :arrowdoubledown: Google Drive: Pretrained Models | Reproduced Experiments :arrowdoubledown: 百度网盘: 预训练模型 | 复现实验
:filefolder: Datasets: :arrowdoubledown: Google Drive :arrowdoubledown: 百度网盘 (提取码:basr)
:chartwithupwardstrend: Training curves in wandb
:computer: Commands for training and testing
:zap: HOWTOs

---

BasicSR (Basic Super Restoration) is an open-source image and video restoration toolbox based on PyTorch, such as super-resolution, denoise, deblurring, JPEG artifacts removal, etc.

BasicSR (Basic Super Restoration) 是一个基于 PyTorch 的开源 图像视频复原工具箱, 比如 超分辨率, 去噪, 去模糊, 去 JPEG 压缩噪声等.

:triangularflagon_post: New Features/Updates

• :whitecheckmark: Oct 5, 2021. Add ECBSR training and testing codes: ECBSR. > ACMMM21: Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices
• :whitecheckmark: Sep 2, 2021. Add SwinIR training and testing codes: SwinIR by Jingyun Liang. More details are in HOWTOs.md
• :whitecheckmark: Aug 5, 2021. Add NIQE, which produces the same results as MATLAB (both are 5.7296 for tests/data/baboon.png).
• :whitecheckmark: July 31, 2021. Add bi-directional video super-resolution codes: BasicVSR and IconVSR. > CVPR21: BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
• More

:sparkles: Projects that use BasicSR

• Real-ESRGAN: A practical algorithm for general image restoration
• GFPGAN: A practical algorithm for real-world face restoration

If you use BasicSR in your open-source projects, welcome to contact me (by email or opening an issue/pull request). I will add your projects to the above list :blush:

---

If BasicSR helps your research or work, please help to :star: this repo or recommend it to your friends. Thanks:blush:
Other recommended projects:
:arrowforward: Real-ESRGAN: A practical algorithm for general image restoration
:arrowforward: GFPGAN: A practical algorithm for real-world face restoration
:arrowforward: facexlib: A collection that provides useful face-relation functions.
:arrowforward: HandyView: A PyQt5-based image viewer that is handy for view and comparison.
_{(ESRGAN, EDVR, DNI, SFTGAN) (HandyView, HandyFigure, HandyCrawler, HandyWriting)}

---

:zap: HOWTOs

We provide simple pipelines to train/test/inference models for a quick start. These pipelines/commands cannot cover all the cases and more details are in the following sections.

| GAN | | | | | | | :------------------- | :--------------------------------------------: | :----------------------------------------------------: | :------- | :--------------------------------------------: | :----------------------------------------------------: | | StyleGAN2 | Train | Inference | | | | | Face Restoration | | | | | | | DFDNet | - | Inference | | | | | Super Resolution | | | | | | | ESRGAN | TODO | TODO | SRGAN | TODO | TODO | | EDSR | TODO | TODO | SRResNet | TODO | TODO | | RCAN | TODO | TODO | SwinIR | Train | Inference | | EDVR | TODO | TODO | DUF | - | TODO | | BasicVSR | TODO | TODO | TOF | - | TODO | | Deblurring | | | | | | | DeblurGANv2 | - | TODO | | | | | Denoise | | | | | | | RIDNet | - | TODO | CBDNet | - | TODO |

:wrench: Dependencies and Installation

For detailed instructions refer to INSTALL.md.

:hourglassflowingsand: TODO List

Please see project boards.

:turtle: Dataset Preparation

• Please refer to DatasetPreparation.md for more details.
• The descriptions of currently supported datasets (torch.utils.data.Dataset classes) are in Datasets.md.

:computer: Train and Test

• Training and testing commands: Please see TrainTest.md for the basic usage.
• Options/Configs: Please refer to Config.md.
• Logging: Please refer to Logging.md.

:european_castle: Model Zoo and Baselines

• The descriptions of currently supported models are in Models.md.
• Pre-trained models and log examples are available in ModelZoo.md.
• We also provide training curves in wandb:

## :memo: Codebase Designs and Conventions Please see [DesignConvention.md](docs/DesignConvention.md) for the designs and conventions of the BasicSR codebase.
The figure below shows the overall framework. More descriptions for each component:
**[Datasets.md](docs/Datasets.md)** | **[Models.md](docs/Models.md)** | **[Config.md](docs/Config.md)** | **[Logging.md](docs/Logging.md)**  ## :scroll: License and Acknowledgement This project is released under the Apache 2.0 license.
More details about **license** and **acknowledgement** are in [LICENSE](LICENSE/README.md). ## :earth_asia: Citations If BasicSR helps your research or work, please consider citing BasicSR.
The following is a BibTeX reference. The BibTeX entry requires the `url` LaTeX package. ``` latex @misc{wang2020basicsr, author = {Xintao Wang and Ke Yu and Kelvin C.K. Chan and Chao Dong and Chen Change Loy}, title = {{BasicSR}: Open Source Image and Video Restoration Toolbox}, howpublished = {\url{https://github.com/xinntao/BasicSR}}, year = {2018} } ``` > Xintao Wang, Ke Yu, Kelvin C.K. Chan, Chao Dong and Chen Change Loy. BasicSR: Open Source Image and Video Restoration Toolbox. , 2018. ## :e-mail: Contact If you have any questions, please email `xintao.wang@outlook.com`.
- **QQ群**: 扫描左边二维码 或者 搜索QQ群号: 320960100   入群答案：互帮互助共同进步 - **微信群**: 我们的群一已经满500人啦，进群二可以扫描中间的二维码；如果进群遇到问题，也可以添加 Liangbin 的个人微信 (右边二维码)，他会在空闲的时候拉大家入群~