[
  {
    "path": "README.md",
    "content": "# Awesome Face Restoration & Enhancement\n[![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome) ![collection](https://img.shields.io/badge/Collection-Keep%20Updating-green) ![visitors](https://api.infinitescript.com/badgen/count?name=sczhou/AwesomeFaceRestoration&ltext=Visitors&color=3977dd)\n\n\nA curated list of awesome face restoration & enhancement papers and resources :whale:, inspired by [awesome-NeRF](https://github.com/yenchenlin/awesome-NeRF). \n\n#### Welcome to add papers and other resources related to this topic [[submit a pull request]](https://github.com/sczhou/Awesome-Face-Restoration/blob/master/how-to-PR.md) :hugs:\n\n## Table of Contents\n\n- [Papers](#papers)\n  - [Face Image Restoration](#face-image-restoration)\n  - [Face Video Restoration](#face-video-restoration)\n- [Datasets](#datasets)\n    - [High-Res Face Dataset](#high-resolution-face-dataset)\n    - [Low-Res Face Dataset](#low-resolution-face-dataset)\n    - [Video Face Dataset](#video-face-dataset)\n    - [Other Face Dataset](#other-face-dataset)\n\n## Papers\n\n### Face Image Restoration\n\n#### Diffusion Model\n\n- `[CVPR 2023]` DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration, Wang et al. [Paper](https://arxiv.org/abs/2303.06885) | [Bibtex](./facebib.bib#L114-L119) \n- `[Arxiv 2022]` DifFace: Blind Face Restoration with Diffused Error Contraction, Yue et al. [Paper](https://arxiv.org/abs/2212.06512) | [Github](https://github.com/zsyOAOA/DifFace) | [Demo](https://huggingface.co/spaces/OAOA/DifFace) | [Bibtex](./facebib.bib#L121-L127)\n\n#### Generative Prior - VQGAN\n- `[NeurIPS 2022]` CodeFormer: Towards Robust Blind Face Restoration with Codebook Lookup Transformer, Zhou et al. [Paper](https://arxiv.org/abs/2206.11253) | [Project](https://shangchenzhou.com/projects/CodeFormer/) | [Github](https://github.com/sczhou/CodeFormer) | [Demo](https://huggingface.co/spaces/sczhou/CodeFormer) | [Bibtex](./facebib.bib#L1-L6)\n\n- `[ECCV 2022]` VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder, Gu et al. [Paper](https://arxiv.org/abs/2205.06803) | [Project](https://ycgu.site/projects/vqfr/) | [Github](https://github.com/sczhou/CodeFormer) | [Bibtex](./facebib.bib#L8-L13)\n\n- `[CVPR 2022]` RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs, Wang et al. [Paper](https://arxiv.org/abs/2201.06374) | [Github](https://github.com/wzhouxiff/RestoreFormer) | [Bibtex](./facebib.bib#L15-L20)\n\n- `[CVPR 2022]` Rethinking Deep Face Restoration. Zhao et al. [Paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhao_Rethinking_Deep_Face_Restoration_CVPR_2022_paper.pdf) | [Bibtex](./facebib.bib#L85-L91)\n\n#### Generative Prior - StyleGAN2\n- `[CVPR 2021]` GFPGAN: Towards Real-World Blind Face Restoration with Generative Facial Prior, Wang et al. [Paper](https://arxiv.org/abs/2101.04061) | [Project](https://xinntao.github.io/projects/gfpgan) | [Github](https://github.com/TencentARC/GFPGAN) | [Demo](https://huggingface.co/spaces/Xintao/GFPGAN) | [Bibtex](./facebib.bib#L43-L48)\n\n- `[CVPR 2021]` GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution, Chan et al. [Paper](https://arxiv.org/abs/2012.00739) | [Project](https://mmlab-ntu.github.io/project/glean/) | [Github](https://github.com/open-mmlab/mmediting) | [Bibtex](./facebib.bib#L36-L41)\n\n- `[CVPR 2021]` GPEN: GAN Prior Embedded Network for Blind Face Restoration in the Wild, Yang et al. [Paper](https://arxiv.org/abs/2105.06070) | [Github](https://github.com/yangxy/GPEN) | [Bibtex](./facebib.bib#L50-L55)\n\n#### GAN Inversion\n- `[CVPR 2020]` PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models, Menon et al. [Paper](https://arxiv.org/abs/2003.03808) | [Github](https://github.com/adamian98/pulse) | [Bibtex](./facebib.bib#L64-L69)\n\n\n#### Dictionary Learning\n- `[TPAMI 2022]` DMDNet: Learning Dual Memory Dictionaries for Blind Face Restoration, Li et al. [Paper](https://arxiv.org/abs/2210.08160) | [Github](https://github.com/csxmli2016/DMDNet) | [CelebRef-HQ Dataset](https://github.com/csxmli2016/DMDNet#celebref-hq-dataset) | [Bibtex](./facebib.bib#L107-L112)\n- `[ECCV 2020]` DFDNet: Blind Face Restoration via Deep Multi-scale Component Dictionaries, Li et al. [Paper](https://arxiv.org/abs/2008.00418) | [Github](https://github.com/csxmli2016/DFDNet) | [Bibtex](./facebib.bib#L22-L27)\n\n#### Reference/Exemplar Prior\n- `[CVPR 2020]` ASFFNet: Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion, Li et al. [Paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Li_Enhanced_Blind_Face_Restoration_With_Multi-Exemplar_Images_and_Adaptive_Spatial_CVPR_2020_paper.pdf) | [Github](https://github.com/csxmli2016/ASFFNet) | [Bibtex](./facebib.bib#L57-L62)\n\n#### Geometry Facial Prior\n- `[CVPR 2021]` PSFRGAN: Progressive Semantic-Aware Style Transformation for Blind Face Restoration, Chen et al. [Paper](https://arxiv.org/abs/2009.08709) | [Github](https://github.com/chaofengc/PSFRGAN) | [Bibtex](./facebib.bib#L29-L34)\n\n#### 3D Face Shape Prior\n- `[CVPR 2022]` SGPN: Blind Face Restoration via Integrating Face Shape and Generative Priors, Zhu et al. [Paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhu_Blind_Face_Restoration_via_Integrating_Face_Shape_and_Generative_Priors_CVPR_2022_paper.pdf) | [Bibtex](./facebib.bib#L71-L76)\n\n#### Personalized Restoration\n- `[ArXiv 2022]` MyStyle: A Personalized Generative Prior, Nitzan et al. [Paper](https://arxiv.org/abs/2203.17272) | [Github](https://github.com/google/mystyle) | [Project](https://mystyle-personalized-prior.github.io/) | [Bibtex](./facebib.bib#L78-L83)\n\n#### Others \n\n- `[TIP 2020]` Learning Spatial Attention for Face Super-Resolution, Chen et al. [Paper](https://arxiv.org/abs/2012.01211) | [Github](https://github.com/chaofengc/Face-SPARNet) | [Bibtex](./facebib.bib#L93-L98)\n\n\n \n\n### Face Video Restoration\n\n- `[CVPRW 2022]` VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution, Xie et al. [Paper](https://arxiv.org/abs/2205.03409) | [Project](https://liangbinxie.github.io/projects/vfhq/) | [Bibtex](./facebib.bib#L100-L105)\n\n## Datasets\n#### High-Resolution Face Dataset\n| Dataset | Resolution | Description |\n| :---: | :---: | :----------    |\n| [FFHQ](https://github.com/NVlabs/ffhq-dataset) | 1024 x 1024 | 7,0000 high-quality face images (usually used for training) |\n| [CelebA-HQ](https://github.com/nperraud/download-celebA-HQ) | 1024 x 1024 | 3,0000 high-quality face images (usually used for evaluation) |\n| [CelebAMask-HQ](https://github.com/switchablenorms/CelebAMask-HQ) | 512 x 512 | 3,0000 face images with 19 facial classes |\n| [CelebRef-HQ](https://github.com/csxmli2016/DMDNet#celebref-hq-dataset) | 512 x 512 | high-quality face images with multiple same-identity references |\n\n#### Low-Resolution Face Dataset\n\n| Dataset | Description |\n| :---: | :----------    |\n| [CelebA](https://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)  | a large-scale face attributes dataset with more than 200K celebrity images |\n| [WIDER-Test](https://shangchenzhou.com/projects/CodeFormer/)  | 970 real-world severely degraded face images from the [WIDER Face dataset](http://shuoyang1213.me/WIDERFACE/) (for test)|\n| [LFW-Test](https://xinntao.github.io/projects/gfpgan)  | 1711 real-world degraded faces collected from the [LFW dataset](https://vis-www.cs.umass.edu/lfw/) (for test)|\n| [WebPhoto-Test](https://xinntao.github.io/projects/gfpgan)  | 407 real-world degraded faces collected from the Internet (for test)|\n| [CelebChild-Test](https://xinntao.github.io/projects/gfpgan)  | 180 real-world degraded child faces collected from the Internet (for test)|\n\n#### Video Face Dataset\n| Dataset | Description |\n| :---: | :----------    |\n| [TalkingHead-1KH](https://github.com/tcwang0509/TalkingHead-1KH)  | 500k video clips, of which about 80k are greater than 512x512 resolution |\n| [VFHQ](https://liangbinxie.github.io/projects/vfhq)  | 16,000 high-fidelity clips of diverse interview scenarios |\n| [CelebV-HQ](https://celebv-hq.github.io/)  | 35,666 video clips involving 15,653 identities and 83 manually labeled facial attributes |\n| [CelebV-Text](https://celebv-text.github.io/)  | 70,000 in-the-wild face video clips covering diverse visual content |\n\n\n\n#### Other Face Dataset\n| Dataset | Description |\n| :---: | :----------    |\n| [CelebA-Dialog](https://github.com/ziqihuangg/CelebA-Dialog)  | a large-scale visual-language face dataset with fine-grained labels and captions|\n| [CelebA-Spoof](https://github.com/ZhangYuanhan-AI/CelebA-Spoof)  | a large-scale face anti-spoofing dataset with rich attributes and spoof types|\n| [PPR10K](https://github.com/csjliang/PPR10K)  | a large-scale portrait photo retouching dataset |"
  },
  {
    "path": "facebib.bib",
    "content": "@InProceedings{zhou2022codeformer,\n    author = {Zhou, Shangchen and Chan, Kelvin C.K. and Li, Chongyi and Loy, Chen Change},\n    title = {Towards Robust Blind Face Restoration with Codebook Lookup TransFormer},\n    booktitle = {NeurIPS},\n    year = {2022}\n}\n\n@InProceedings{gu2022vqfr,\n    title = {VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder},\n    author = {Gu, Yuchao and Wang, Xintao and Xie, Liangbin and Dong, Chao and Li, Gen and Shan, Ying and Cheng, Ming-Ming},\n    year = {2022},\n    booktitle = {ECCV}\n}\n\n@InProceedings{wang2022restoreformer,\n    title = {RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs},\n    author = {Wang, Zhouxia and Zhang, Jiawei and Chen, Runjian and Wang, Wenping and Luo, Ping},\n    booktitle = {CVPR},\n    year={2022}\n}\n\n@InProceedings{Li_2020_ECCV,\n    author = {Li, Xiaoming and Chen, Chaofeng and Zhou, Shangchen and Lin, Xianhui and Zuo, Wangmeng and Zhang, Lei},\n    title = {Blind Face Restoration via Deep Multi-scale Component Dictionaries},\n    booktitle = {ECCV},\n    year = {2020}\n}\n\n@inproceedings{ChenPSFRGAN,\n    author = {Chen, Chaofeng and Li, Xiaoming and Lingbo, Yang and Lin, Xianhui and Zhang, Lei and Wong, KKY},\n    title = {Progressive Semantic-Aware Style Transformation for Blind Face Restoration},\n    Journal = {CVPR},\n    year = {2021}\n}\n\n@InProceedings{chan2021glean,\n    author = {Chan, Kelvin CK and Wang, Xintao and Xu, Xiangyu and Gu, Jinwei and Loy, Chen Change},\n    title = {GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution},\n    booktitle = {CVPR},\n    year = {2021}\n}\n\n@InProceedings{wang2021gfpgan,\n    author = {Xintao Wang and Yu Li and Honglun Zhang and Ying Shan},\n    title = {Towards Real-World Blind Face Restoration with Generative Facial Prior},\n    booktitle = {CVPR},\n    year = {2021}\n}\n\n@inproceedings{Yang2021GPEN,\n    title={GAN Prior Embedded Network for Blind Face Restoration in the Wild},\n    author={Tao Yang, Peiran Ren, Xuansong Xie, and Lei Zhang},\n    booktitle={CVPR},\n    year={2021}\n}\n\n@InProceedings{Li_2020_CVPR,\n    author = {Li, Xiaoming and Li, Wenyu and Ren, Dongwei and Zhang, Hongzhi and Wang, Meng and Zuo, Wangmeng},\n    title = {Enhanced Blind Face Restoration with Multi-Exemplar Images and Adaptive Spatial Feature Fusion},\n    booktitle = {CVPR},\n    year = {2020}\n}\n\n@inproceedings{menon2020pulse,\n    title={Pulse: Self-supervised photo upsampling via latent space exploration of generative models},\n    author={Menon, Sachit and Damian, Alexandru and Hu, Shijia and Ravi, Nikhil and Rudin, Cynthia},\n    booktitle={CVPR},\n    year={2020}\n}\n\n@inproceedings{zhu2022blind,\n    title={Blind Face Restoration via Integrating Face Shape and Generative Priors},\n    author={Zhu, Feida and Zhu, Junwei and Chu, Wenqing and Zhang, Xinyi and Ji, Xiaozhong and Wang, Chengjie and Tai, Ying},\n    booktitle={CVPR},\n    year={2022}\n}\n\n@article{nitzan2022mystyle,\n    title={MyStyle: A Personalized Generative Prior},\n    author={Nitzan, Yotam and Aberman, Kfir and He, Qiurui and Liba, Orly and Yarom, Michal and Gandelsman, Yossi and Mosseri, Inbar and Pritch, Yael and Cohen-Or, Daniel},\n    journal={arXiv preprint arXiv:2203.17272},\n    year={2022}\n}\n\n@inproceedings{zhao2022rethinking,\n  title={Rethinking Deep Face Restoration},\n  author={Zhao, Yang and Su, Yu-Chuan and Chu, Chun-Te and Li, Yandong and Renn, Marius and Zhu, Yukun and Chen, Changyou and Jia, Xuhui},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages={7652--7661},\n  year={2022}\n}\n\n@InProceedings{ChenSPARNet,\n    author = {Chen, Chaofeng and Gong, Dihong and Wang, Hao and Li, Zhifeng and Wong, Kwan-Yee K.},\n    title = {Learning Spatial Attention for Face Super-Resolution},\n    Journal = {IEEE Transactions on Image Processing (TIP)},\n    year = {2020}\n}\n\n@InProceedings{xie2022vfhq,\n      author = {Liangbin Xie and Xintao Wang and Honglun Zhang and Chao Dong and Ying Shan},\n      title = {VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution},\n      booktitle={The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},\n      year = {2022}\n}\n\n@article{li2022dmdnet,\n    title = {Learning Dual Memory Dictionaries for Blind Face Restoration},\n    author = {Li, Xiaoming and Zhang, Shiguang and Zhou, Shangchen and Zhang, Lei and Zuo, Wangmeng},\n    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},\n    year = {2022}\n}\n\n@article{wang2023dr2,\n    title = {DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration},\n    author = {Wang, Zhixin and Zhang, Xiaoyun and Zhang, Ziying and Zheng, Huangjie and Zhou, Mingyuan and Zhang, Ya and Wang, Yanfeng},\n    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n    year = {2023}\n}\n\n@misc{yue2022diface,\n  url = {https://arxiv.org/abs/2212.06512},\n  author = {Yue, Zongsheng and Loy, Chen Change},\n  title = {DifFace: Blind Face Restoration with Diffused Error Contraction},\n  publisher = {arXiv},\n  year = {2022},\n}"
  },
  {
    "path": "how-to-PR.md",
    "content": "1. Put the bibtex at the **END** of `facebib.bib`. \n   \n2. Modify the corresponding list in the `README.md` and follow the format:\n\n    `[CONFERENCE YEAR] ABBREVIATION: TITLE, AUTHOR. | PAPER | OPTIONAL Link(s) | BIBTEX`\n  \nFor example:\n- `[NeurIPS 2022]` CodeFormer: Towards Robust Blind Face Restoration with Codebook Lookup Transformer, Zhou et al. [Paper](https://arxiv.org/abs/2206.11253) | [Project](https://shangchenzhou.com/projects/CodeFormer/) | [Github](https://github.com/sczhou/CodeFormer) | [Demo](https://huggingface.co/spaces/sczhou/CodeFormer) | [Bibtex](./facebib.bib#L1-L6)"
  }
]