{"id":15028151,"url":"https://github.com/xinntao/edvr","last_synced_at":"2025-10-08T19:11:28.263Z","repository":{"id":41070630,"uuid":"180380038","full_name":"xinntao/EDVR","owner":"xinntao","description":"Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR and this repo is a mirror of BasicSR.","archived":false,"fork":false,"pushed_at":"2021-08-09T14:20:10.000Z","size":2562,"stargazers_count":1525,"open_issues_count":120,"forks_count":317,"subscribers_count":55,"default_branch":"master","last_synced_at":"2025-05-23T02:05:34.283Z","etag":null,"topics":["basicsr","edvr","pytorch"],"latest_commit_sha":null,"homepage":"https://github.com/xinntao/BasicSR","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xinntao.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE/LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-04-09T14:03:10.000Z","updated_at":"2025-05-22T10:43:25.000Z","dependencies_parsed_at":"2022-08-28T21:10:51.783Z","dependency_job_id":null,"html_url":"https://github.com/xinntao/EDVR","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/xinntao/EDVR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinntao%2FEDVR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinntao%2FEDVR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinntao%2FEDVR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinntao%2FEDVR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xinntao","download_url":"https://codeload.github.com/xinntao/EDVR/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinntao%2FEDVR/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000701,"owners_count":26082805,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["basicsr","edvr","pytorch"],"created_at":"2024-09-24T20:07:42.617Z","updated_at":"2025-10-08T19:11:28.246Z","avatar_url":"https://github.com/xinntao.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"#### EDVR has been merged into [BasicSR](https://github.com/xinntao/BasicSR). This GitHub repo is a mirror of [BasicSR](https://github.com/xinntao/BasicSR). Recommend to use [BasicSR](https://github.com/xinntao/BasicSR), and open issues, pull requests, etc in [BasicSR](https://github.com/xinntao/BasicSR).\nNote that this version is not compatible with previous versions. If you want to use previous ones, please refer to the `old_version` branch.\n\n---\n\n# :rocket: [BasicSR](https://github.com/xinntao/BasicSR)\n\n[English](README.md) **|** [简体中文](README_CN.md) \u0026emsp; [GitHub](https://github.com/xinntao/BasicSR) **|** [Gitee码云](https://gitee.com/xinntao/BasicSR)\n\n\u003ca href=\"https://drive.google.com/drive/folders/1G_qcpvkT5ixmw5XoN6MupkOzcK1km625?usp=sharing\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" height=\"18\" alt=\"google colab logo\"\u003e\u003c/a\u003e Google Colab: [GitHub Link](colab) **|** [Google Drive Link](https://drive.google.com/drive/folders/1G_qcpvkT5ixmw5XoN6MupkOzcK1km625?usp=sharing) \u003cbr\u003e\n:m: [Model Zoo](docs/ModelZoo.md) :arrow_double_down: Google Drive: [Pretrained Models](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) **|** [Reproduced Experiments](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)\n:arrow_double_down: 百度网盘: [预训练模型](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g) **|** [复现实验](https://pan.baidu.com/s/1UElD6q8sVAgn_cxeBDOlvQ) \u003cbr\u003e\n:file_folder: [Datasets](docs/DatasetPreparation.md) :arrow_double_down: [Google Drive](https://drive.google.com/drive/folders/1gt5eT293esqY0yr1Anbm36EdnxWW_5oH?usp=sharing) :arrow_double_down: [百度网盘](https://pan.baidu.com/s/1AZDcEAFwwc1OC3KCd7EDnQ) (提取码:basr)\u003cbr\u003e\n:chart_with_upwards_trend: [Training curves in wandb](https://app.wandb.ai/xintao/basicsr) \u003cbr\u003e\n:computer: [Commands for training and testing](docs/TrainTest.md) \u003cbr\u003e\n:zap: [HOWTOs](#zap-howtos)\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*.\u003cbr\u003e\n\u003csub\u003e([ESRGAN](https://github.com/xinntao/ESRGAN), [EDVR](https://github.com/xinntao/EDVR), [DNI](https://github.com/xinntao/DNI), [SFTGAN](https://github.com/xinntao/SFTGAN))\u003c/sub\u003e\n\u003csub\u003e([HandyView](https://github.com/xinntao/HandyView), [HandyFigure](https://github.com/xinntao/HandyFigure), [HandyCrawler](https://github.com/xinntao/HandyCrawler), [HandyWriting](https://github.com/xinntao/HandyWriting))\u003c/sub\u003e\n\n## :sparkles: New Features\n\n- Nov 29, 2020. Add **ESRGAN** and **DFDNet** [colab demo](colab).\n- Sep 8, 2020. Add **blind face restoration** inference codes: [DFDNet](https://github.com/csxmli2016/DFDNet).\n- Aug 27, 2020. Add **StyleGAN2 training and testing** codes: [StyleGAN2](https://github.com/rosinality/stylegan2-pytorch).\n\n\u003cdetails\u003e\n  \u003csummary\u003eMore\u003c/summary\u003e\n\u003cul\u003e\n  \u003cli\u003e Sep 8, 2020. Add \u003cb\u003eblind face restoration\u003c/b\u003e inference codes: \u003cb\u003eDFDNet\u003c/b\u003e. \u003cbr\u003e \u003ci\u003e\u003cfont color=\"#DCDCDC\"\u003eECCV20: Blind Face Restoration via Deep Multi-scale Component Dictionaries\u003c/font\u003e\u003c/i\u003e \u003cbr\u003e \u003ci\u003e\u003cfont color=\"#DCDCDC\"\u003eXiaoming Li, Chaofeng Chen, Shangchen Zhou, Xianhui Lin, Wangmeng Zuo and Lei Zhang\u003c/font\u003e\u003c/i\u003e \u003c/li\u003e\n  \u003cli\u003e Aug 27, 2020. Add \u003cb\u003eStyleGAN2\u003c/b\u003e training and testing codes. \u003cbr\u003e \u003ci\u003e\u003cfont color=\"#DCDCDC\"\u003eCVPR20: Analyzing and Improving the Image Quality of StyleGAN\u003c/font\u003e\u003c/i\u003e \u003cbr\u003e \u003ci\u003e\u003cfont color=\"#DCDCDC\"\u003eTero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen and Timo Aila\u003c/font\u003e\u003c/i\u003e \u003c/li\u003e\n  \u003cli\u003eAug 19, 2020. A \u003cb\u003ebrand-new\u003c/b\u003e BasicSR v1.0.0 online.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\n## :zap: HOWTOs\n\nWe provides simple pipelines to train/test/inference models for 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* |  |  | |\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## :wrench: Dependencies and Installation\n\n- Python \u003e= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))\n- [PyTorch \u003e= 1.3](https://pytorch.org/)\n- NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads)\n\n1. Clone repo\n\n    ```bash\n    git clone https://github.com/xinntao/BasicSR.git\n    ```\n\n1. Install dependent packages\n\n    ```bash\n    cd BasicSR\n    pip install -r requirements.txt\n    ```\n\n1. Install BasicSR\n\n    Please run the following commands in the **BasicSR root path** to install BasicSR:\u003cbr\u003e\n    (Make sure that your GCC version: gcc \u003e= 5) \u003cbr\u003e\n    If you do not need the cuda extensions: \u003cbr\u003e\n    \u0026emsp;[*dcn* for EDVR](basicsr/models/ops)\u003cbr\u003e\n    \u0026emsp;[*upfirdn2d* and *fused_act* for StyleGAN2](basicsr/models/ops)\u003cbr\u003e\n    please add `--no_cuda_ext` when installing\n\n    ```bash\n    python setup.py develop --no_cuda_ext\n    ```\n\n    If you use the EDVR and StyleGAN2 model, the above cuda extensions are necessary.\n\n    ```bash\n    python setup.py develop\n    ```\n\n    You may also want to specify the CUDA paths:\n\n      ```bash\n      CUDA_HOME=/usr/local/cuda \\\n      CUDNN_INCLUDE_DIR=/usr/local/cuda \\\n      CUDNN_LIB_DIR=/usr/local/cuda \\\n      python setup.py develop\n      ```\n\nNote that BasicSR is only tested in Ubuntu, and may be not suitable for Windows. You may try [Windows WSL with CUDA supports](https://docs.microsoft.com/en-us/windows/win32/direct3d12/gpu-cuda-in-wsl) :-) (It is now only available for insider build with Fast ring).\n\n## :hourglass_flowing_sand: TODO List\n\nPlease see [project boards](https://github.com/xinntao/BasicSR/projects).\n\n## :turtle: Dataset Preparation\n\n- Please refer to **[DatasetPreparation.md](docs/DatasetPreparation.md)** for more details.\n- The descriptions of currently supported datasets (`torch.utils.data.Dataset` classes) are in [Datasets.md](docs/Datasets.md).\n\n## :computer: Train and Test\n\n- **Training and testing commands**: Please see **[TrainTest.md](docs/TrainTest.md)** for the basic usage.\n- **Options/Configs**: Please refer to [Config.md](docs/Config.md).\n- **Logging**: Please refer to [Logging.md](docs/Logging.md).\n\n## :european_castle: Model Zoo and Baselines\n\n- The descriptions of currently supported models are in [Models.md](docs/Models.md).\n- **Pre-trained models and log examples** are available in **[ModelZoo.md](docs/ModelZoo.md)**.\n- We also provide **training curves** in [wandb](https://app.wandb.ai/xintao/basicsr):\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://app.wandb.ai/xintao/basicsr\" target=\"_blank\"\u003e\n   \u003cimg src=\"./assets/wandb.jpg\" height=\"280\"\u003e\n\u003c/a\u003e\u003c/p\u003e\n\n## :memo: Codebase Designs and Conventions\n\nPlease see [DesignConvention.md](docs/DesignConvention.md) for the designs and conventions of the BasicSR codebase.\u003cbr\u003e\nThe figure below shows the overall framework. More descriptions for each component: \u003cbr\u003e\n**[Datasets.md](docs/Datasets.md)**\u0026emsp;|\u0026emsp;**[Models.md](docs/Models.md)**\u0026emsp;|\u0026emsp;**[Config.md](Config.md)**\u0026emsp;|\u0026emsp;**[Logging.md](docs/Logging.md)**\n\n![overall_structure](./assets/overall_structure.png)\n\n## :scroll: License and Acknowledgement\n\nThis project is released under the Apache 2.0 license.\u003cbr\u003e\nMore details about **license** and **acknowledgement** are in [LICENSE](LICENSE/README.md).\n\n## :earth_asia: Citations\n\nIf BasicSR helps your research or work, please consider citing BasicSR.\u003cbr\u003e\nThe following is a BibTeX reference. The BibTeX entry requires the `url` LaTeX package.\n\n``` latex\n@misc{wang2020basicsr,\n  author =       {Xintao Wang and Ke Yu and Kelvin C.K. Chan and\n                  Chao Dong and Chen Change Loy},\n  title =        {BasicSR},\n  howpublished = {\\url{https://github.com/xinntao/BasicSR}},\n  year =         {2020}\n}\n```\n\n\u003e Xintao Wang, Ke Yu, Kelvin C.K. Chan, Chao Dong and Chen Change Loy. BasicSR. https://github.com/xinntao/BasicSR, 2020.\n\n## :e-mail: Contact\n\nIf you have any question, please email `xintao.wang@outlook.com`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinntao%2Fedvr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxinntao%2Fedvr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinntao%2Fedvr/lists"}