<p align="center">
<img src="assets/basicsr_xpixel_logo.png" height=120>
</p>
## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
<div align="center">
[](https://github.com/xinntao/BasicSR/blob/master/LICENSE.txt)
[](https://pypi.org/project/basicsr/)
[](https://lgtm.com/projects/g/xinntao/BasicSR/context:python)
[](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/pylint.yml)
[](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/publish-pip.yml)
[](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/gitee-mirror.yml)
</div>
<div align="center">
⚡[**HowTo**](#-HOWTOs) **|** 🔧[**Installation**](docs/INSTALL.md) **|** 💻[**Training Commands**](docs/TrainTest.md) **|** 🐢[**DatasetPrepare**](docs/DatasetPreparation.md) **|** 🏰[**Model Zoo**](docs/ModelZoo.md)
📕[**中文解读文档**](https://github.com/XPixelGroup/BasicSR-docs) **|** 📊 [**Plot scripts**](scripts/plot) **|** 📝[Introduction](docs/introduction.md) **|** <a href="https://github.com/XPixelGroup/BasicSR/tree/master/colab"><img src="https://colab.research.google.com/assets/colab-badge.svg" height="18" alt="google colab logo"></a> **|** ⏳[TODO List](https://github.com/xinntao/BasicSR/projects) **|** ❓[FAQ](docs/FAQ.md)
</div>
🚀 We add [BasicSR-Examples](https://github.com/xinntao/BasicSR-examples), which provides guidance and templates of using BasicSR as a python package. 🚀 <br>
📢 **技术交流QQ群**：**320960100**   入群答案：**互帮互助共同进步** <br>
🧭 [入群二维码](#-contact) (QQ、微信)    [入群指南 (腾讯文档)](https://docs.qq.com/doc/DYXBSUmxOT0xBZ05u) <br>
---
BasicSR (**Basic** **S**uper **R**estoration) is an open-source **image and video restoration** toolbox based on PyTorch, such as super-resolution, denoise, deblurring, JPEG artifacts removal, *etc*.<br>
BasicSR (**Basic** **S**uper **R**estoration) 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.
🚩 **New Features/Updates**
- ✅ July 26, 2022. Add plot scripts 📊[Plot](scripts/plot).
- ✅ May 9, 2022. BasicSR joins [XPixel](http://xpixel.group/).
- ✅ Oct 5, 2021. Add **ECBSR training and testing** codes: [ECBSR](https://github.com/xindongzhang/ECBSR).
> ACMMM21: Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices
- ✅ Sep 2, 2021. Add **SwinIR training and testing** codes: [SwinIR](https://github.com/JingyunLiang/SwinIR) by [Jingyun Liang](https://github.com/JingyunLiang). More details are in [HOWTOs.md](docs/HOWTOs.md#how-to-train-swinir-sr)
- ✅ Aug 5, 2021. Add NIQE, which produces the same results as MATLAB (both are 5.7296 for tests/data/baboon.png).
- ✅ July 31, 2021. Add **bi-directional video super-resolution** codes: [**BasicVSR** and IconVSR](https://arxiv.org/abs/2012.02181).
> CVPR21: BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
- **[More](docs/history_updates.md)**
---
If BasicSR helps your research or work, please help to ⭐ this repo or recommend it to your friends. Thanks😊 <br>
Other recommended projects:<br>
▶️ [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN): A practical algorithm for general image restoration<br>
▶️ [GFPGAN](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration <br>
▶️ [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions.<br>
▶️ [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison. <br>
▶️ [HandyFigure](https://github.com/xinntao/HandyFigure): Open source of paper figures <br>
<sub>([ESRGAN](https://github.com/xinntao/ESRGAN), [EDVR](https://github.com/xinntao/EDVR), [DNI](https://github.com/xinntao/DNI), [SFTGAN](https://github.com/xinntao/SFTGAN))</sub>
<sub>([HandyCrawler](https://github.com/xinntao/HandyCrawler), [HandyWriting](https://github.com/xinntao/HandyWriting))</sub>
---
## ⚡ 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](docs/HOWTOs.md#How-to-train-StyleGAN2) | [Inference](docs/HOWTOs.md#How-to-inference-StyleGAN2) | | | |
| **Face Restoration** | | | | | |
| DFDNet | - | [Inference](docs/HOWTOs.md#How-to-inference-DFDNet) | | | |
| **Super Resolution** | | | | | |
| ESRGAN | *TODO* | *TODO* | SRGAN | *TODO* | *TODO* |
| EDSR | *TODO* | *TODO* | SRResNet | *TODO* | *TODO* |
| RCAN | *TODO* | *TODO* | SwinIR | [Train](docs/HOWTOs.md#how-to-train-swinir-sr) | [Inference](docs/HOWTOs.md#how-to-inference-swinir-sr) |
| EDVR | *TODO* | *TODO* | DUF | - | *TODO* |
| BasicVSR | *TODO* | *TODO* | TOF | - | *TODO* |
| **Deblurring** | | | | | |
| DeblurGANv2 | - | *TODO* | | | |
| **Denoise** | | | | | |
| RIDNet | - | *TODO* | CBDNet | - | *TODO* |
## ✨ **Projects that use BasicSR**
- [**Real-ESRGAN**](https://github.com/xinntao/Real-ESRGAN): A practical algorithm for general image restoration
- [**GFPGAN**](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration
If you use `BasicSR` in your open-source projects, welcome to contact me (by [email](#-contact) or opening an issue/pull request). I will add your projects to the above list 😊
## 📜 License and Acknowledgement
This project is released under the [Apache 2.0 license](LICENSE.txt).<br>
More details about **license** and **acknowledgement** are in [LICENSE](LICENSE/README.md).
## 🌏 Citations
If BasicSR helps your research or work, please cite BasicSR.<br>
The following is a BibTeX reference. The BibTeX entry requires the `url` LaTeX package.
``` latex
@misc{basicsr,
author = {Xintao Wang and Liangbin Xie and Ke Yu and Kelvin C.K. Chan and Chen Change Loy and Chao Dong},
title = {{BasicSR}: Open Source Image and Video Restoration Toolbox},
howpublished = {\url{https://github.com/XPixelGroup/BasicSR}},
year = {2022}
}
```
> Xintao Wang, Liangbin Xie, Ke Yu, Kelvin C.K. Chan, Chen Change Loy and Chao Dong. BasicSR: Open Source Image and Video Restoration Toolbox. <https://github.com/xinntao/BasicSR>, 2022.
## 📧 Contact
If you have any questions, please email `xintao.alpha@gmail.com`, `xintao.wang@outlook.com`.
<br>
- **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**: 我们的一群已经满500人啦，二群也超过200人了；进群可以添加 Liangbin 的个人微信 (右边二维码)，他会在空闲的时候拉大家入群~
<p align="center">
<img src="https://user-images.githubusercontent.com/17445847/134879983-6f2d663b-16e7-49f2-97e1-7c53c8a5f71a.jpg" height="300">  
<img src="https://user-images.githubusercontent.com/17445847/139572512-8e192aac-00fa-432b-ac8e-a33026b019df.png" height="300">
</p>
 (start from 2022-11-06)
Raw data
{
"_id": null,
"home_page": "https://github.com/xinntao/BasicSR",
"name": "basicsr-volta",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "computer vision,restoration,super resolution",
"author": "Xintao Wang",
"author_email": "xintao.wang@outlook.com",
"download_url": "https://files.pythonhosted.org/packages/08/84/406bd49d74ff594892b6cb0ec3a5ecaeea97b34cd44709b456c4ed235f9a/basicsr-volta-1.4.4.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <img src=\"assets/basicsr_xpixel_logo.png\" height=120>\n</p>\n\n## <div align=\"center\"><b><a href=\"README.md\">English</a> | <a href=\"README_CN.md\">\u7b80\u4f53\u4e2d\u6587</a></b></div>\n\n<div align=\"center\">\n\n[](https://github.com/xinntao/BasicSR/blob/master/LICENSE.txt)\n[](https://pypi.org/project/basicsr/)\n[](https://lgtm.com/projects/g/xinntao/BasicSR/context:python)\n[](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/pylint.yml)\n[](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/publish-pip.yml)\n[](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/gitee-mirror.yml)\n\n</div>\n\n<div align=\"center\">\n\n\u26a1[**HowTo**](#-HOWTOs) **|** \ud83d\udd27[**Installation**](docs/INSTALL.md) **|** \ud83d\udcbb[**Training Commands**](docs/TrainTest.md) **|** \ud83d\udc22[**DatasetPrepare**](docs/DatasetPreparation.md) **|** \ud83c\udff0[**Model Zoo**](docs/ModelZoo.md)\n\n\ud83d\udcd5[**\u4e2d\u6587\u89e3\u8bfb\u6587\u6863**](https://github.com/XPixelGroup/BasicSR-docs) **|** \ud83d\udcca [**Plot scripts**](scripts/plot) **|** \ud83d\udcdd[Introduction](docs/introduction.md) **|** <a href=\"https://github.com/XPixelGroup/BasicSR/tree/master/colab\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" height=\"18\" alt=\"google colab logo\"></a> **|** \u23f3[TODO List](https://github.com/xinntao/BasicSR/projects) **|** \u2753[FAQ](docs/FAQ.md)\n</div>\n\n\ud83d\ude80 We add [BasicSR-Examples](https://github.com/xinntao/BasicSR-examples), which provides guidance and templates of using BasicSR as a python package. \ud83d\ude80 <br>\n\ud83d\udce2 **\u6280\u672f\u4ea4\u6d41QQ\u7fa4**\uff1a**320960100**   \u5165\u7fa4\u7b54\u6848\uff1a**\u4e92\u5e2e\u4e92\u52a9\u5171\u540c\u8fdb\u6b65** <br>\n\ud83e\udded [\u5165\u7fa4\u4e8c\u7ef4\u7801](#-contact) (QQ\u3001\u5fae\u4fe1)    [\u5165\u7fa4\u6307\u5357 (\u817e\u8baf\u6587\u6863)](https://docs.qq.com/doc/DYXBSUmxOT0xBZ05u) <br>\n\n---\n\nBasicSR (**Basic** **S**uper **R**estoration) is an open-source **image and video restoration** toolbox based on PyTorch, such as super-resolution, denoise, deblurring, JPEG artifacts removal, *etc*.<br>\nBasicSR (**Basic** **S**uper **R**estoration) \u662f\u4e00\u4e2a\u57fa\u4e8e PyTorch \u7684\u5f00\u6e90 \u56fe\u50cf\u89c6\u9891\u590d\u539f\u5de5\u5177\u7bb1, \u6bd4\u5982 \u8d85\u5206\u8fa8\u7387, \u53bb\u566a, \u53bb\u6a21\u7cca, \u53bb JPEG \u538b\u7f29\u566a\u58f0\u7b49.\n\n\ud83d\udea9 **New Features/Updates**\n\n- \u2705 July 26, 2022. Add plot scripts \ud83d\udcca[Plot](scripts/plot).\n- \u2705 May 9, 2022. BasicSR joins [XPixel](http://xpixel.group/).\n- \u2705 Oct 5, 2021. Add **ECBSR training and testing** codes: [ECBSR](https://github.com/xindongzhang/ECBSR).\n > ACMMM21: Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices\n- \u2705 Sep 2, 2021. Add **SwinIR training and testing** codes: [SwinIR](https://github.com/JingyunLiang/SwinIR) by [Jingyun Liang](https://github.com/JingyunLiang). More details are in [HOWTOs.md](docs/HOWTOs.md#how-to-train-swinir-sr)\n- \u2705 Aug 5, 2021. Add NIQE, which produces the same results as MATLAB (both are 5.7296 for tests/data/baboon.png).\n- \u2705 July 31, 2021. Add **bi-directional video super-resolution** codes: [**BasicVSR** and IconVSR](https://arxiv.org/abs/2012.02181).\n > CVPR21: BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond\n- **[More](docs/history_updates.md)**\n\n---\n\nIf BasicSR helps your research or work, please help to \u2b50 this repo or recommend it to your friends. Thanks\ud83d\ude0a <br>\nOther recommended projects:<br>\n\u25b6\ufe0f [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN): A practical algorithm for general image restoration<br>\n\u25b6\ufe0f [GFPGAN](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration <br>\n\u25b6\ufe0f [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions.<br>\n\u25b6\ufe0f [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison. <br>\n\u25b6\ufe0f [HandyFigure](https://github.com/xinntao/HandyFigure): Open source of paper figures <br>\n<sub>([ESRGAN](https://github.com/xinntao/ESRGAN), [EDVR](https://github.com/xinntao/EDVR), [DNI](https://github.com/xinntao/DNI), [SFTGAN](https://github.com/xinntao/SFTGAN))</sub>\n<sub>([HandyCrawler](https://github.com/xinntao/HandyCrawler), [HandyWriting](https://github.com/xinntao/HandyWriting))</sub>\n\n---\n\n## \u26a1 HOWTOs\n\nWe provide simple pipelines to train/test/inference models for a quick start.\nThese pipelines/commands cannot cover all the cases and more details are in the following sections.\n\n| GAN | | | | | |\n| :------------------- | :--------------------------------------------: | :----------------------------------------------------: | :------- | :--------------------------------------------: | :----------------------------------------------------: |\n| StyleGAN2 | [Train](docs/HOWTOs.md#How-to-train-StyleGAN2) | [Inference](docs/HOWTOs.md#How-to-inference-StyleGAN2) | | | |\n| **Face Restoration** | | | | | |\n| DFDNet | - | [Inference](docs/HOWTOs.md#How-to-inference-DFDNet) | | | |\n| **Super Resolution** | | | | | |\n| ESRGAN | *TODO* | *TODO* | SRGAN | *TODO* | *TODO* |\n| EDSR | *TODO* | *TODO* | SRResNet | *TODO* | *TODO* |\n| RCAN | *TODO* | *TODO* | SwinIR | [Train](docs/HOWTOs.md#how-to-train-swinir-sr) | [Inference](docs/HOWTOs.md#how-to-inference-swinir-sr) |\n| EDVR | *TODO* | *TODO* | DUF | - | *TODO* |\n| BasicVSR | *TODO* | *TODO* | TOF | - | *TODO* |\n| **Deblurring** | | | | | |\n| DeblurGANv2 | - | *TODO* | | | |\n| **Denoise** | | | | | |\n| RIDNet | - | *TODO* | CBDNet | - | *TODO* |\n\n## \u2728 **Projects that use BasicSR**\n\n- [**Real-ESRGAN**](https://github.com/xinntao/Real-ESRGAN): A practical algorithm for general image restoration\n- [**GFPGAN**](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration\n\nIf you use `BasicSR` in your open-source projects, welcome to contact me (by [email](#-contact) or opening an issue/pull request). I will add your projects to the above list \ud83d\ude0a\n\n## \ud83d\udcdc License and Acknowledgement\n\nThis project is released under the [Apache 2.0 license](LICENSE.txt).<br>\nMore details about **license** and **acknowledgement** are in [LICENSE](LICENSE/README.md).\n\n## \ud83c\udf0f Citations\n\nIf BasicSR helps your research or work, please cite BasicSR.<br>\nThe following is a BibTeX reference. The BibTeX entry requires the `url` LaTeX package.\n\n``` latex\n@misc{basicsr,\n author = {Xintao Wang and Liangbin Xie and Ke Yu and Kelvin C.K. Chan and Chen Change Loy and Chao Dong},\n title = {{BasicSR}: Open Source Image and Video Restoration Toolbox},\n howpublished = {\\url{https://github.com/XPixelGroup/BasicSR}},\n year = {2022}\n}\n```\n\n> Xintao Wang, Liangbin Xie, Ke Yu, Kelvin C.K. Chan, Chen Change Loy and Chao Dong. BasicSR: Open Source Image and Video Restoration Toolbox. <https://github.com/xinntao/BasicSR>, 2022.\n\n## \ud83d\udce7 Contact\n\nIf you have any questions, please email `xintao.alpha@gmail.com`, `xintao.wang@outlook.com`.\n\n<br>\n\n- **QQ\u7fa4**: \u626b\u63cf\u5de6\u8fb9\u4e8c\u7ef4\u7801 \u6216\u8005 \u641c\u7d22QQ\u7fa4\u53f7: 320960100 \u2003 \u5165\u7fa4\u7b54\u6848\uff1a\u4e92\u5e2e\u4e92\u52a9\u5171\u540c\u8fdb\u6b65\n- **\u5fae\u4fe1\u7fa4**: \u6211\u4eec\u7684\u4e00\u7fa4\u5df2\u7ecf\u6ee1500\u4eba\u5566\uff0c\u4e8c\u7fa4\u4e5f\u8d85\u8fc7200\u4eba\u4e86\uff1b\u8fdb\u7fa4\u53ef\u4ee5\u6dfb\u52a0 Liangbin \u7684\u4e2a\u4eba\u5fae\u4fe1 (\u53f3\u8fb9\u4e8c\u7ef4\u7801)\uff0c\u4ed6\u4f1a\u5728\u7a7a\u95f2\u7684\u65f6\u5019\u62c9\u5927\u5bb6\u5165\u7fa4~\n\n<p align=\"center\">\n <img src=\"https://user-images.githubusercontent.com/17445847/134879983-6f2d663b-16e7-49f2-97e1-7c53c8a5f71a.jpg\" height=\"300\">  \n <img src=\"https://user-images.githubusercontent.com/17445847/139572512-8e192aac-00fa-432b-ac8e-a33026b019df.png\" height=\"300\">\n</p>\n\n (start from 2022-11-06)\n",
"bugtrack_url": null,
"license": "Apache License 2.0",
"summary": "Open Source Image and Video Super-Resolution Toolbox",
"version": "1.4.4",
"project_urls": {
"Homepage": "https://github.com/xinntao/BasicSR"
},
"split_keywords": [
"computer vision",
"restoration",
"super resolution"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fd4c7992644f26e904bedd63007d1170a15cd6b0c1200b62e1765988d2c23994",
"md5": "5173b5980882a3828a48d58d7aabe0d9",
"sha256": "372036c0baac5d63e1a2afe44f628f73b42c27c6484ce54670039ca1d523df02"
},
"downloads": -1,
"filename": "basicsr_volta-1.4.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5173b5980882a3828a48d58d7aabe0d9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 223277,
"upload_time": "2024-03-18T19:23:47",
"upload_time_iso_8601": "2024-03-18T19:23:47.046885Z",
"url": "https://files.pythonhosted.org/packages/fd/4c/7992644f26e904bedd63007d1170a15cd6b0c1200b62e1765988d2c23994/basicsr_volta-1.4.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "0884406bd49d74ff594892b6cb0ec3a5ecaeea97b34cd44709b456c4ed235f9a",
"md5": "6ca60d40e2b22e2e0484972bc663da02",
"sha256": "90af59768e5f86e5dd503dbd30b1aaeed10e1d8558061cc6bee05b6b3a8b425b"
},
"downloads": -1,
"filename": "basicsr-volta-1.4.4.tar.gz",
"has_sig": false,
"md5_digest": "6ca60d40e2b22e2e0484972bc663da02",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 177565,
"upload_time": "2024-03-18T19:23:49",
"upload_time_iso_8601": "2024-03-18T19:23:49.560716Z",
"url": "https://files.pythonhosted.org/packages/08/84/406bd49d74ff594892b6cb0ec3a5ecaeea97b34cd44709b456c4ed235f9a/basicsr-volta-1.4.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-18 19:23:49",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "xinntao",
"github_project": "BasicSR",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "basicsr-volta"
}
JSON
