English | 简体中文 GitHub | Gitee码云
🚀 我们添加了 BasicSR-Examples, 它提供了使用BasicSR的指南以及模板 (以python package的形式) 🚀
📢 技术交流QQ群:320960100 入群答案:互帮互助共同进步
🧭 入群二维码 (QQ、微信) 入群指南 (腾讯文档)
Google Colab: GitHub Link | Google Drive Link
Ⓜ️ 模型库: ⏬ 百度网盘: 预训练模型 | 复现实验
⏬ Google Drive: Pretrained Models | Reproduced Experiments
📁 数据: ⏬ 百度网盘 (提取码:basr) ⏬ Google Drive
📈 wandb的训练曲线
💻 训练和测试的命令
⚡ HOWTOs
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.
🚩 新的特性/更新
ACMMM21: Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices
CVPR21: BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
✨ 使用 BasicSR 的项目
如果你的开源项目中使用了BasicSR
, 欢迎联系我 (邮件或者开一个issue/pull request)。我会将你的开源项目添加到上面的列表中 😊
如果 BasicSR 对你有所帮助,欢迎 ⭐ 这个仓库或推荐给你的朋友。Thanks😊
其他推荐的项目:
▶️ Real-ESRGAN: 通用图像复原的实用算法
▶️ GFPGAN: 真实场景人脸复原的实用算法
▶️ facexlib: 提供实用的人脸相关功能的集合
▶️ HandyView: 基于PyQt5的 方便的看图比图工具
(ESRGAN, EDVR, DNI, SFTGAN)
(HandyView, HandyFigure, HandyCrawler, HandyWriting)
我们提供了简单的流程来快速上手 训练/测试/推理 模型. 这些命令并不能涵盖所有用法, 更多的细节参见下面的部分.
GAN | |||||
---|---|---|---|---|---|
StyleGAN2 | 训练 | 测试 | |||
Face Restoration | |||||
DFDNet | - | 测试 | |||
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 |
For detailed instructions refer to INSTALL.md.
参见 project boards.
torch.utils.data.Dataset
类), 参见 Datasets_CN.md.参见 DesignConvention_CN.md.
下图概括了整体的框架. 每个模块更多的描述参见:
Datasets_CN.md | Models_CN.md | Config_CN.md | Logging_CN.md
本项目使用 Apache 2.0 license.
更多关于许可和致谢, 请参见 LICENSE.
如果 BasicSR 对你有所帮助, 可以考虑引用BasicSR.
下面是一个 BibTex 引用条目, 它需要 url
LaTeX package.
@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 = {2020}
}
Xintao Wang, Ke Yu, Kelvin C.K. Chan, Chao Dong and Chen Change Loy. BasicSR: Open Source Image and Video Restoration Toolbox. https://github.com/xinntao/BasicSR, 2020.
若有任何问题, 请电邮 xintao.wang@outlook.com
.
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》