Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/TaoWangzj/Awesome-Face-Restoration

A comprehensive list of recources (papers, repositories etc.) about face restoration methods.
https://github.com/TaoWangzj/Awesome-Face-Restoration
List: Awesome-Face-Restoration
awesome-list blind-face-restoration face-artifact-removal face-deblurring face-denoising face-restoration face-super-resolution ffhq
Last synced: 3 months ago
JSON representation
A comprehensive list of recources (papers, repositories etc.) about face restoration methods.
Host: GitHub
URL: https://github.com/TaoWangzj/Awesome-Face-Restoration
Owner: TaoWangzj
Created: 2022-11-08T02:43:11.000Z (almost 2 years ago)
Default Branch: main
Last Pushed: 2024-04-02T07:31:54.000Z (7 months ago)
Last Synced: 2024-05-23T06:08:21.197Z (5 months ago)
Topics: awesome-list, blind-face-restoration, face-artifact-removal, face-deblurring, face-denoising, face-restoration, face-super-resolution, ffhq
Homepage:
Size: 8.78 MB
Stars: 375
Watchers: 4
Forks: 30
Open Issues: 2
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

awesome-ai-list-guide - Awesome-Face-Restoration
StarryDivineSky - TaoWangzj/Awesome-Face-Restoration
ultimate-awesome - Awesome-Face-Restoration - A comprehensive list of recources (papers, repositories etc.) about face restoration methods. (Other Lists / PowerShell Lists)
README

        



  
Deep Face Restoartion: Denoise,

Super-Resolution, Deblur and Artifact Removal 

  A comprehensive list of resources for Deep Face Restoartion

    


    


    


    Suggest new item

    


    Report Bug

  


This repository provides a summary of deep learning-based face restoration algorithms. 

Our classification is based on the review paper "A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal".

|  |  |  | | |

| :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |:----------------------------------------------------------: |:----------------------------------------------------------: |

|           Blind Face Restoration                          |                      Face Super-Resolution                                | Face Deblurring        |Face Denoising    | Face Artifact Removal

## Survey paper

T. Wang, k. Zhang, X. Chen, W. Luo, J. Deng, T. Lu, X. Cao, W. Liu, H. Li, and S. Zafeiriou “A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal,” arXiv preprint arXiv:2211.02831, 2022. [[pdf](https://arxiv.org/pdf/2211.02831.pdf)]

```

@article{wang2022survey

  title={A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal},

  author={Wang, Tao, and Zhang, kaihao, and Chen, Xuanxi and Luo, Wenhan and Deng, Jiankang and Lu, Tong and Cao, Xiaochun and Liu, Wei and Li, Hongdong and Zafeiriou, Stefanos},

  journal={arXiv preprint arXiv:2211.02831},

  year={2022}

}

```

See our paper for more details.

If you have any suggestions, feel free to contact me (e-mail: [email protected]). Thanks.

## Table of contents

- [Surveys](#surveys)

- [Deep Blind Face Restoration](#deep-blind-face-restoration)

- [Deep Face Super-Resolution](#deep-face-super-resolution)

- [Deep Face Deblurring](#deep-face-deblurring)

- [Deep Face Denoising](#deep-face-denoising)

- [Deep Face Artifact Removal](#deep-face-artifact-removal)

- [Other Related Works](#other-related-works)

- [Image Quality Assessment](#image-quality-assessment)

- [Benchmark Datasets](#benchmark-datasets)

  - [Recommended Datasets](#recommended-datasets)

  - [All Datasets](#all-datasets)

## Surveys

|year|Pub|Title|Link|

|:----:|:----:|:----:|:----:|

|2022|Arxiv|A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal|\[[paper](https://arxiv.org/pdf/2211.02831.pdf)\]|

## Deep Blind Face Restoration  

|Year
|Pub|Title|Links|Arch|

|:---:|:----:|:----:|:----:|:----:|

|2018|ECCV|Learning Warped Guidance for Blind Face Restoration|\[[paper](https://openaccess.thecvf.com/content_ECCV_2018/papers/Xiaoming_Li_Learning_Warped_Guidance_ECCV_2018_paper.pdf)\]\[[code](https://github.com/csxmli2016/GFRNet)\]|CNN|

|2018|CVPR|FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors|\[[paper](https://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_FSRNet_End-to-End_Learning_CVPR_2018_paper.pdf)\]\[[code](https://github.com/tyshiwo/FSRNet)\]|CNN|

|2019|IJCV|Identity-preserving Face Recovery from Stylized Portraits|\[[paper](https://Arxiv.org/pdf/1904.04241.pdf)\]\[code\]|GAN|

|2020|ECCV|Blind Face Restoration via Deep Multi-scale Component Dictionaries|\[[paper](https://Arxiv.org/pdf/2008.00418)\]\[[code](https://github.com/csxmli2016/DFDNet)\]|CNN|

|2020|CVPR|Enhanced Blind Face Restoration with Multi-Exemplar Images 
and Adaptive Spatial Feature Fusion|\[[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Li_Enhanced_Blind_Face_Restoration_With_Multi-Exemplar_Images_and_Adaptive_Spatial_CVPR_2020_paper.pdf)\]\[[code](https://github.com/csxmli2016/ASFFNet)\]|CNN|

|2020|MM|HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment|\[[paper](https://Arxiv.org/pdf/2005.05005.pdf)\]\[[code](https://github.com/Lotayou/Face-Renovation)\]|GAN|

|2020|CVPR|Image Processing Using Multi-Code GAN Prior|\[[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Gu_Image_Processing_Using_Multi-Code_GAN_Prior_CVPR_2020_paper.pdf)\]\[[code](https://github.com/genforce/mganprior)\]|GAN|

|2021|TPAMI|Face Restoration via Plug-and-Play 3D Facial Priors|\[[paper](https://www.zora.uzh.ch/id/eprint/214478/1/ZORA214478.pdf)\]\[code\]|CNN|

|2021|CVPR|Progressive Semantic-Aware Style Transformation for Blind Face Restoration|\[[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Progressive_Semantic-Aware_Style_Transformation_for_Blind_Face_Restoration_CVPR_2021_paper.pdf)\]\[[code](https://github.com/chaofengc/PSFRGAN)\]|GAN|

|2021|CVPR|Towards Real-World Blind Face Restoration with Generative Facial Prior|\[[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Towards_Real-World_Blind_Face_Restoration_With_Generative_Facial_Prior_CVPR_2021_paper.pdf)\]\[[code](https://xinntao.github.io/projects/gfpgan)\]|GAN|

|2021|CVPR|GAN Prior Embedded Network for Blind Face Restoration in the Wild|\[[paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Yang_GAN_Prior_Embedded_Network_for_Blind_Face_Restoration_in_the_CVPR_2021_paper.pdf)\]\[[code](https://github.com/yangxy/GPEN)\]|GAN|

|2022|Arxiv|Multi-prior learning via neural architecture search for blind face restoration|\[[paper](https://Arxiv.org/pdf/2206.13962.pdf)\]\[[code](https://github.com/YYJ1anG/MFPSNet)\]|CNN|

|2022|CVPR|Blind Face Restoration via Integrating Face Shape and Generative Priors|\[[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhu_Blind_Face_Restoration_via_Integrating_Face_Shape_and_Generative_Priors_CVPR_2022_paper.pdf)\]~~\[[code](https://github.com/TencentYoutuResearch/BFR-SGPN)\]~~|GAN|

|2022|CVPR|RestoreFormer: High-Quality Blind Face Restoration 
 from Undegraded Key-Value Pairs|\[[paper](https://Arxiv.org/pdf/2201.06374.pdf)\]\[[code](https://github.com/wzhouxiff/RestoreFormer)\]|ViT|

|2022|NeurIPS|Towards Robust Blind Face Restoration with Codebook Lookup Transformer|\[[paper](https://Arxiv.org/pdf/2206.11253.pdf)\]\[[code](https://github.com/sczhou/CodeFormer)\]|ViT|

|2022|AAAI|Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration|\[[paper](https://arxiv.org/pdf/2203.08444.pdf)\]\[[code](https://github.com/jianzhangcs/panini)\]|GAN|

|2022|Arxiv|FaceFormer: Scale-aware Blind Face Restoration with Transformers|\[[paper](https://Arxiv.org/pdf/2207.09790.pdf)\]\[code\]|ViT|

|2022|Arxiv|Blind Face Restoration: Benchmark Datasets and a Baseline Model|\[[paper](https://Arxiv.org/pdf/2206.03697.pdf)\]\[[code](https://github.com/bitzpy/blind-face-restoration-benchmark-datasets-and-a-baseline-model)\]|ViT|

|2022|ECCV|VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder|\[[paper](https://Arxiv.org/pdf/2205.06803.pdf)\]\[[code](https://github.com/TencentARC/VQFR)\]|CNN|  

|2022|TPAMI|Learning Dual Memory Dictionaries for Blind Face Restoration|\[[paper](https://arxiv.org/pdf/2210.08160.pdf)\]\[[code](https://github.com/csxmli2016/DMDNet)\]|CNN|

|2022|Arxiv|Difface: Blind Face Restoration with Diffused Error Contraction|\[[paper](https://arxiv.org/pdf/2212.06512.pdf?trk=public_post_comment-text)\]\[[code](https://github.com/zsyOAOA/DifFace)\]|Diffusion|

|2023|CVPR|DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration|\[[paper](https://arxiv.org/abs/2303.06885)\]\[[code](https://github.com/Kaldwin0106/DR2_Drgradation_Remover)\]|Diffusion|

|2023|CVPR|TFRGAN: Leveraging Text Information for Blind Face Restoration with Extreme Degradation|\[[paper](https://openaccess.thecvf.com/content/CVPR2023W/MULA/papers/Xie_TFRGAN_Leveraging_Text_Information_for_Blind_Face_Restoration_With_Extreme_CVPRW_2023_paper.pdf)\]\[code\]|GAN|

|2023|TCSVT|DEAR-GAN: Degradation-Aware Face Restoration With GAN Prior|\[[paper](https://ieeexplore.ieee.org/abstract/document/10044117)\]\[code\]|GAN|

|2023|FSP|Degradation Learning and Skip-Transformer for Blind Face Restoration|\[[paper](https://www.frontiersin.org/articles/10.3389/frsip.2023.1106465/full)\]\[code\]|GAN|

|2023|WACV|AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Models|\[[paper](https://openaccess.thecvf.com/content/WACV2023/papers/Nair_AT-DDPM_Restoring_Faces_Degraded_by_Atmospheric_Turbulence_Using_Denoising_Diffusion_WACV_2023_paper.pdf)\]\[[code](https://github.com/Nithin-GK/AT-DDPM)\]|Diffusion|

|2023|ACMMM|DiffBFR: Bootstrapping Diffusion Model for Blind Face Restoration|\[[paper](https://dl.acm.org/doi/pdf/10.1145/3581783.3611731)\]\[code\]|Diffusion|

|2024|TCSVT|Towards Real-World Blind Face Restoration with Generative Diffusion Prior|\[[paper](https://arxiv.org/pdf/2312.15736.pdf)\]\[[code](https://github.com/chenxx89/BFRffusion)\]|Diffusion|

|2024|WACV|Diffuse and Restore: A Region-Adaptive Diffusion Model for Identity-Preserving Blind Face Restoration|\[[paper](https://openaccess.thecvf.com/content/WACV2024/papers/Suin_Diffuse_and_Restore_A_Region-Adaptive_Diffusion_Model_for_Identity-Preserving_Blind_WACV_2024_paper.pdf)\]\[code\]|Diffusion|

|2024|AAAI|Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery|\[[paper](https://ojs.aaai.org/index.php/AAAI/article/view/27889/27803)\]\[code\]|Diffusion|

## Deep Face Super-Resolution  

|Year
|Pub|Title|Links|Arch|

|:---:|:----:|:----:|:----:|:----:|

|2015|AAAI|Learning Face Hallucination in the Wild|\[[paper](https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewPDFInterstitial/9752/9824)\]\[code\]|CNN|

|2016|ECCV|Deep Cascaded Bi-Network for Face Hallucination|\[[paper](http://home.ie.cuhk.edu.hk/~ccloy/files/eccv_2016_hallucination.pdf)\]\[code\]|CNN|

|2016|ECCV|Ultra-Resolving Face Images by Discriminative Generative Networks|\[[paper](https://link.springer.com/content/pdf/10.1007/978-3-319-46454-1_20.pdf)\]\[[code](https://github.com/jiaming-wang/URDGN)\]|GAN|

|2017|CVPR|Attention-Aware Face Hallucination via Deep Reinforcement Learning|\[[paper](https://openaccess.thecvf.com/content_cvpr_2017/papers/Cao_Attention-Aware_Face_Hallucination_CVPR_2017_paper.pdf)\]\[code\]|CNN|

|2017|CVPR|Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by 
Transformative Discriminative Autoencoders|\[[paper](https://openaccess.thecvf.com/content_cvpr_2017/papers/Yu_Hallucinating_Very_Low-Resolution_CVPR_2017_paper.pdf)\]\[code\]|CNN|

|2017|ICCV|Learning to Super-Resolve Blurry Face and Text Images|\[[paper](https://openaccess.thecvf.com/content_ICCV_2017/papers/Xu_Learning_to_Super-Resolve_ICCV_2017_paper.pdf)\]\[[code](https://sites.google.com/view/xiangyuxu/deblursr_iccv17)\]|GAN|

|2017|AAAI|Face Hallucination with Tiny Unaligned Images 
 by Transformative Discriminative Neural Networks|\[[paper](https://ojs.aaai.org/index.php/AAAI/article/view/11206)\]\[code\]|GAN|

|2018|ECCV|Face Super-resolution Guided by Facial Component Heatmaps|\[[paper](https://openaccess.thecvf.com/content_ECCV_2018/papers/Xin_Yu_Face_Super-resolution_Guided_ECCV_2018_paper.pdf)\]\[code\]|CNN|

|2018|CVPR|Super-FAN: Integrated facial landmark localization and 
 super-resolution of real-world low resolution faces in arbitrary poses with gans|\[[paper](https://openaccess.thecvf.com/content_cvpr_2018/papers/Bulat_Super-FAN_Integrated_Facial_CVPR_2018_paper.pdf)\]\[code\]|GAN|

|2018|ECCV|To learn image super-resolution,
 use a GAN to learn how to do image degradation first|\[[paper](https://openaccess.thecvf.com/content_ECCV_2018/papers/Adrian_Bulat_To_learn_image_ECCV_2018_paper.pdf)\]\[[code](https://github.com/jingyang2017/Face-and-Image-super-resolution)\]|GAN|

|2019|CVPRW|Exemplar Guided Face Image Super-Resolution without Facial Landmarks|\[[paper](https://openaccess.thecvf.com/content_CVPRW_2019/papers/NTIRE/Dogan_Exemplar_Guided_Face_Image_Super-Resolution_Without_Facial_Landmarks_CVPRW_2019_paper.pdf)\]\[[code](https://github.com/berkdogan2/GWAInet)\]|CNN|

|2019|BMVC|Progressive Face Super-Resolution via Attention to Facial Landmark|\[[paper](https://Arxiv.org/pdf/1908.08239.pdf)\]\[[code](https://github.com/DeokyunKim/Progressive-Face-Super-Resolution)\]|CNN|

|2020|WACV|Component Attention Guided Face Super-Resolution Network: CAGFace|\[[paper](https://openaccess.thecvf.com/content_WACV_2020/papers/Kalarot_Component_Attention_Guided_Face_Super-Resolution_Network_CAGFace_WACV_2020_paper.pdf)\]\[[code](https://github.com/SeungyounShin/CAGFace)\]|CNN|

|2020|TNNLS|Dual-Path Deep Fusion Network for Face Image Hallucination|\[[paper](https://ieeexplore.ieee.org/abstract/document/9229100)\]\[code\]|CNN|

|2019|NEUCOM|On potentials of regularized Wasserstein generative adversarial networks for
 realistic hallucination of tiny faces|\[[paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231219310203)\]\[code\]|GAN|

|2020|CVPR|PULSE: Self-Supervised Photo Upsampling via 
Latent Space Exploration of Generative Models|\[[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Menon_PULSE_Self-Supervised_Photo_Upsampling_via_Latent_Space_Exploration_of_Generative_CVPR_2020_paper.pdf)\]\[[code](https://github.com/adamian98/pulse)\]|GAN|

|2021|TBBIS|E-ComSupResNet: Enhanced Face Super-Resolution Through Compact Network|\[[paper](https://ieeexplore.ieee.org/abstract/document/9353687)\]\[code\]|CNN|

|2021|MM|Face Hallucination via Split-Attention in Split-Attention Network|\[[paper](https://Arxiv.org/pdf/2010.11575.pdf)\]\[[code](https://github.com/mdswyz/SISN-Face-Hallucination)\]|CNN|

|2021|ICIP|Progressive Face Super-Resolution with Non-Parametric Facial Prior Enhancement|\[[paper](https://ieeexplore.ieee.org/abstract/document/9506610)\]\[[code](https://github.com/BenjaminJonghyun/NPFNet)\]|GAN|

|2022|CVPR|GCFSR: a Generative and Controllable Face Super Resolution Method 
 Without Facial and GAN Priors|\[[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/He_GCFSR_A_Generative_and_Controllable_Face_Super_Resolution_Method_Without_CVPR_2022_paper.pdf)\]\[[code](https://github.com/hejingwenhejingwen/GCFSR)\]|GAN|

|2022|TPAMI|EDFace-Celeb-1 M: Benchmarking Face Hallucination with a Million-scale Dataset|\[[paper](https://arxiv.org/pdf/2110.05031.pdf)\]\[[code](https://github.com/HDCVLab/EDFace-Celeb-1M)\]|CNN|

|2023|TIP|Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution|\[[paper](https://ieeexplore.ieee.org/abstract/document/10036448)\]\[[code](https://github.com/HaoHou-98/SCGAN)\]|GAN|

|2023|AAAI|GAN Prior based Null-Space Learning for Consistent Super-Resolution|\[[paper](https://arxiv.org/pdf/2211.13524.pdf)\]\[[code](https://github.com/wyhuai/RND)\]|GAN|

|2023|CVPR|Spatial-Frequency Mutual Learning for Face Super-Resolution|\[[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Spatial-Frequency_Mutual_Learning_for_Face_Super-Resolution_CVPR_2023_paper.pdf)\]\[[code](https://github.com/wcy-cs/SFMNet)\]|CNN| 

|2023|TMM|Sctanet: A Spatial Attention-guided Cnn-transformer Aggregation Network for Deep Face Image Super-Resolution|\[[paper](https://ieeexplore.ieee.org/abstract/document/10023973)\]\[code\]|ViT|

|2023|TMM|An Efficient Latent Style Guided Transformer-CNN Framework for Face Super-Resolution|\[[paper](https://ieeexplore.ieee.org/abstract/document/10145603)\]\[[code](https://github.com/FVL2020/ELSFace)\]|ViT|

|2023|TMM|Exploiting Multi-scale Parallel Self-attention and Local Variation via Dual-branch Transformer-CNN Structure for Face Super-resolution|\[[paper](https://ieeexplore.ieee.org/abstract/document/10207832)\]\[[code](https://github.com/jingang-cv/DBTC)\]|ViT|

|2023|PR|A Composite Network Model for Face Super-Resolution with Multi-Order Head Attention Facial Priors|\[[paper](https://www.sciencedirect.com/science/article/pii/S0031320323002030)\]\[code\]|ViT|

|2023|TIP|Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution|\[[paper](https://arxiv.org/pdf/2205.03777.pdf)\]\[[code](https://github.com/HaoHou-98/SCGAN)\]|GAN|

|2023|AS|A Multi-Scale Deep Back-Projection Backbone for Face Super-Resolution with Diffusion Models|\[[paper](https://www.mdpi.com/2076-3417/13/14/8110)\][code]|Diffusion|

|2023|TIM|Deep HyFeat Based Attention in Attention Model for Face Super-Resolution|\[[paper](https://ieeexplore.ieee.org/abstract/document/10044127)\][code]|CNN|

|2023|PRL|Attentive ExFeat based Deep Generative Adversarial Network for Noise Robust Face Super-resolution|\[[paper](https://ieeexplore.ieee.org/abstract/document/10044127)\][code]|GAN|

|2023|NN|Self-attention Learning Network for Face Super-resolution|\[[paper](https://www.sciencedirect.com/science/article/pii/S0893608023000060)\][code]|CNN|

## Deep Face Deblurring   

|Year
|Pub|Title|Links|Arch|

|:---:|:----:|:----:|:----:|:----:|

|2017|Arxiv|DeepDeblur: Fast one-step blurry face images restoration|\[[paper](https://Arxiv.org/pdf/1711.09515.pdf)\]\[code\]|CNN|

|2018|CVPR|Deep Semantic Face Deblurring|\[[paper](https://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Deep_Semantic_Face_CVPR_2018_paper.pdf)\]\[[code](https://github.com/joanshen0508/Deep-Semantic-Face-Deblurring)\]|CNN|

|2020|IJCV|Exploiting Semantics for Face Image Deblurring|\[[paper](https://Arxiv.org/pdf/2001.06822.pdf)\]\[[code](https://github.com/BenjaminJonghyun/NPFNet)\]|CNN|

|2020|TIP|Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks|\[[paper](https://Arxiv.org/pdf/1907.13106.pdf)\]\[[code](https://github.com/rajeevyasarla/UMSN-Face-Deblurring)\]|CNN|

|2020|MM|HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment|\[[paper](https://Arxiv.org/pdf/2005.05005.pdf)\]\[[code](https://github.com/Lotayou/Face-Renovation)\]|GAN|

|2020|AAAI|Learning to deblur face images via sketch synthesis|\[[paper](https://ojs.aaai.org/index.php/AAAI/article/view/6818/6672)\]\[code\]|CNN|

|2022|TOG|Face Deblurring using Dual Camera Fusion on Mobile Phones|\[[paper](https://dl.acm.org/doi/abs/10.1145/3528223.3530131)\]\[[code](https://www.wslai.net/publications/fusion_deblur/)\]|CNN|

|2022|WACV|Deep Feature Prior Guided Face Deblurring|\[[paper](https://openaccess.thecvf.com/content/WACV2022/papers/Jung_Deep_Feature_Prior_Guided_Face_Deblurring_WACV_2022_paper.pdf)\]\[code\]|CNN|

|2022|Arxiv|Multi-prior learning via neural architecture search for blind face restoration|\[[paper](https://Arxiv.org/pdf/2206.13962.pdf)\]\[[code](https://github.com/YYJ1anG/MFPSNet)\]|CNN|

|2022|Arxiv|Blind Face Restoration: Benchmark Datasets and a Baseline Model|\[[paper](https://Arxiv.org/pdf/2206.03697.pdf)\]\[[code](https://github.com/bitzpy/blind-face-restoration-benchmark-datasets-and-a-baseline-model)\]|ViT|

|2022|SIGGRAPH|Face Deblurring using Dual Camera Fusion on Mobile Phones|\[[paper](https://www.wslai.net/publications/fusion_deblur/)\][code]|CNN|

  

## Deep Face Denoising

|Year|Pub|Title|Links|Arch|

|:---:|:----:|:----:|:----:|:----:|

|2020|MM|HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment|\[[paper](https://Arxiv.org/pdf/2005.05005.pdf)\]\[[code](https://github.com/Lotayou/Face-Renovation)\]|GAN|

|2022|Arxiv|Multi-prior learning via neural architecture search for blind face restoration|\[[paper](https://Arxiv.org/pdf/2206.13962.pdf)\]\[[code](https://github.com/YYJ1anG/MFPSNet)\]|CNN|

|2022|Arxiv|Blind Face Restoration: Benchmark Datasets and a Baseline Model|\[[paper](https://Arxiv.org/pdf/2206.03697.pdf)\]\[[code](https://github.com/bitzpy/blind-face-restoration-benchmark-datasets-and-a-baseline-model)\]|ViT|

  

## Deep Face Artifact Removal

|Year
|Pub|Title|Links|Arch|

|:---:|:----:|:----:|:----:|:----:|

|2020|MM|HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment|\[[paper](https://Arxiv.org/pdf/2005.05005.pdf)\]\[[code](https://github.com/Lotayou/Face-Renovation)\]|GAN|

|2022|Arxiv|Blind Face Restoration: Benchmark Datasets and a Baseline Model|\[[paper](https://Arxiv.org/pdf/2206.03697.pdf)\]\[[code](https://github.com/bitzpy/blind-face-restoration-benchmark-datasets-and-a-baseline-model)\]|ViT|

|2022|Arxiv|Multi-prior learning via neural architecture search for blind face restoration|\[[paper](https://Arxiv.org/pdf/2206.13962.pdf)\]\[[code](https://github.com/YYJ1anG/MFPSNet)\]|CNN|

## Other Related Works

- CG-GAN: Class-Attribute Guided Generative Adversarial Network for Old Photo Restoration, Liu et al., ACMM 2021. [Link](https://dl.acm.org/doi/abs/10.1145/3474085.3475666)

- Old Photo Restoration via Deep Latent Space Translation, Wan et al., TPAMI 2022. [Link](https://ieeexplore.ieee.org/abstract/document/9744329/)

- Demeshnet: Blind Face Inpainting for Deep Meshface Verification, Zhang et al. TIP 2017. [Link](https://ieeexplore.ieee.org/abstract/document/8067496)

- Face Inpainting based on High-level Facial Attributes, Jampour et al., CVIU 2017. [Link](https://www.sciencedirect.com/science/article/pii/S1077314217300930)

- ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo, Lei et al., CVPR 2022. [Link](https://openaccess.thecvf.com/content/CVPR2022/papers/Lei_ABPN_Adaptive_Blend_Pyramid_Network_for_Real-Time_Local_Retouching_of_CVPR_2022_paper.pdf)

- Autoretouch: Automatic Professional Face Retouching, Shafaei et al., WACV 2021. [Link](https://openaccess.thecvf.com/content/WACV2021/papers/Shafaei_AutoRetouch_Automatic_Professional_Face_Retouching_WACV_2021_paper.pdf)

- Network Architecture Search for Face Enhancement, Yasarla et al., Arxiv 2021. [Link](https://arxiv.org/abs/2105.06528)

- Towards Automatic Face-to-face Translation, KR, R et al., ACMMM 2019. [Link](https://dl.acm.org/doi/abs/10.1145/3343031.3351066)

- A Sketchtransformer Network for Face Photo-sketch Synthesis, Zhu et al., IJCAI 2021. [Link](https://www.ijcai.org/proceedings/2021/0187.pdf)

## Image Quality Assessment

|Method|Type|Code/Ref|

|---|---|---|

|PSNR (Peak Signal-to-Noise Ratio)|Full-Reference|[Code](https://github.com/XPixelGroup/BasicSR/blob/master/basicsr/metrics/psnr_ssim.py)|

|SSIM (Structural Similarity Index Measurement)|Full-Reference|[Code](https://github.com/XPixelGroup/BasicSR/blob/master/basicsr/metrics/psnr_ssim.py)|

|MS-SSIM (Multi-scale Structural Similarity Index Measurement)|Full-Reference|[Code](https://github.com/VainF/pytorch-msssim/blob/master/pytorch_msssim/ssim.py)|

|LPIPS (Learned Perceptual Image Patch Similarity)|Full-Reference|[Code](https://github.com/richzhang/PerceptualSimilarity)|

|NIQE (Naturalness Image Quality Evaluator)|Non-Reference|[Code](https://github.com/utlive/niqe)|

|FID (Fréchet Inception Distance)|Non-Reference|[Code](https://github.com/bioinf-jku/TTUR)|

|PI (Perceptual Index)|Non-Reference|[Code](https://github.com/chaoma99/sr-metric)|

|MOS (Mean Opinion Score)|Subject-Metric|[Ref](https://www.itu.int/rec/R-REC-BT.500/)|

|iPrecision|Task Driven-Metric|[Ref](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhao_Rethinking_Deep_Face_Restoration_CVPR_2022_paper.pdf)|

|iRecall|Task Driven-Metric|[Ref](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhao_Rethinking_Deep_Face_Restoration_CVPR_2022_paper.pdf)|

|LLE (Landmark Localization Error)|Task Driven-Metric|[Code](https://github.com/Lotayou/Face-Renovation)|

|Deg (Identity Distance)|Task Driven-Metric|[Code](https://github.com/TencentARC/GFPGAN)|

|AFLD (Average Face Landmark Distance)|Task Driven-Metric|[Code](https://github.com/bitzpy/Blind-Face-Restoration-Benchmark-Datasets-and-a-Baseline-Model)|

|AFICS (Average Face ID Cosine Similarity)|Task Driven-Metric|[Code](https://github.com/bitzpy/Blind-Face-Restoration-Benchmark-Datasets-and-a-Baseline-Model)|

## Benchmark Datasets

### Recommended Datasets

|Dataset|Usage|Quantity|Type|

|:----:|:----:|:----:|:----:|

|[EDFace-Celeb](https://github.com/HDCVLab/EDFace-Celeb-1M)|training&testing|>1M|paired dataset|

|[PFHQ](https://github.com/chenxx89/BFRffusion)|training|60,000|paired dataset|

|[FFHQ](https://github.com/NVlabs/ffhq-dataset)|training|70,000|non-paired dataset|

|[CelebChild-Test](https://xinntao.github.io/projects/gfpgan)|testing|180|non-paired real-world dataset|

|[WebPhoto-Test](https://xinntao.github.io/projects/gfpgan)|testing|407|non-paired real-world dataset|

|[LFW-Test](https://xinntao.github.io/projects/gfpgan)|testing|1,711|non-paired real-world dataset|

### All Datasets

|Dataset|Paper|Year|

|:----:|:----:|:----:|

|[BioID](https://www.bioid.com/facedb/)|[Robust face detection using the hausdorff distance](https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.28.6915&rep=rep1&type=pdf)|2001|

|[LFW](http://vis-www.cs.umass.edu/lfw/)|[Labeled faces in the wild: A database forstudying face recognition in unconstrainedenvironments](https://hal.inria.fr/inria-00321923/file/Huang_long_eccv2008-lfw.pdf)|2008|

|[Pubfig](https://www1.cs.columbia.edu/CAVE/databases/pubfig/)|[Attribute and similar classifiers for face verification](https://neerajkumar.org/projects/facesearch/base/software/base/publications/base/papers/nk_iccv2009_attrs.pdf)|2009|

|[Multi-PIE](https://www.cs.cmu.edu/afs/cs/project/PIE/MultiPie/Multi-Pie/Home.html)|[Multi-PIE](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2873597/)|2010|

|[AFLW](https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/aflw/)|[Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization](https://www.tugraz.at/fileadmin/user_upload/Institute/ICG/Documents/lrs/pubs/koestinger_befit_11.pdf)|2011|

|[Helen](http://www.ifp.illinois.edu/~vuongle2/helen)|[Interactive Facial Feature Localization](https://link.springer.com/content/pdf/10.1007/978-3-642-33712-3_49.pdf)|2012|

|[300W](https://ibug.doc.ic.ac.uk/resources/300-W/)|[300 Faces in-the-Wild Challenge: The first facial landmark localization Challenge](https://www.cv-foundation.org/openaccess/content_iccv_workshops_2013/W11/papers/Sagonas_300_Faces_in-the-Wild_2013_ICCV_paper.pdf)|2013|

|[CASIA-WebFace](https://pan.baidu.com/share/init?surl=hQCOD4Kr66MOW0_PE8bL0w)
(Password: y3wj)|[Learning Face Representation from Scratch](https://Arxiv.org/pdf/1411.7923.pdf)|2014|

|[CelebA](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)|[Deep Learning Face Attributes in the Wild](https://openaccess.thecvf.com/content_iccv_2015/papers/Liu_Deep_Learning_Face_ICCV_2015_paper.pdf)|2015|

|[IMDB-WIKI](https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/)|[DEX: Deep EXpectation of apparent age from a single image](https://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w11/papers/Rothe_DEX_Deep_EXpectation_ICCV_2015_paper.pdf)|2015|

|[LSUN](https://www.yf.io/p/lsun)|[LSUN: Construction of a Large-Scale Image Dataset using Deep Learning with Humans in the Loop](https://Arxiv.org/pdf/1506.03365v3.pdf)|2015|

|[VGGFace](https://www.robots.ox.ac.uk/~vgg/software/vgg_face/)|[Deep Face Recognition](https://ora.ox.ac.uk/objects/uuid:a5f2e93f-2768-45bb-8508-74747f85cad1/download_file?file_format=pdf&safe_filename=parkhi15.pdf&type_of_work=Confer)|2015|

|[300W-LP](http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm)|[Face Alignment Across Large Poses: A 3D Solution](https://openaccess.thecvf.com/content_cvpr_2016/papers/Zhu_Face_Alignment_Across_CVPR_2016_paper.pdf)|2016|

|[VoxCeleb1](https://www.robots.ox.ac.uk/~vgg/data/voxceleb/vox1.html)|[VoxCeleb: a large-scale speaker identification dataset](https://Arxiv.org/pdf/1706.08612.pdf)|2017|

|[LS3D-W](https://www.adrianbulat.com/face-alignment)|[How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://openaccess.thecvf.com/content_ICCV_2017/papers/Bulat_How_Far_Are_ICCV_2017_paper.pdf)|2017|

|[LS3D-W balanced](https://www.adrianbulat.com/face-alignment)|[How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://openaccess.thecvf.com/content_ICCV_2017/papers/Bulat_How_Far_Are_ICCV_2017_paper.pdf)|2017|

|[Menpo](https://github.com/jiankangdeng/MenpoBenchmark)|[The Menpo Facial Landmark Localisation Challenge: A step towards the solution](https://openaccess.thecvf.com/content_cvpr_2017_workshops/w33/papers/Zafeiriou_The_Menpo_Facial_CVPR_2017_paper.pdf)|2017|

|[VGGFace2](https://www.robots.ox.ac.uk/~vgg/data/vgg_face2/)|[VGGFace2: A dataset for recognising faces across pose and age](https://Arxiv.org/pdf/1710.08092.pdf)|2018|

|[VoxCeleb2](https://www.robots.ox.ac.uk/~vgg/data/voxceleb/)|[Voxceleb2: Deep speaker recognition](https://Arxiv.org/pdf/1806.05622.pdf)|2018|

|[FFHQ](https://github.com/NVlabs/ffhq-dataset)|[A Style-Based Generator Architecture for Generative Adversarial Networks](https://openaccess.thecvf.com/content_CVPR_2019/papers/Karras_A_Style-Based_Generator_Architecture_for_Generative_Adversarial_Networks_CVPR_2019_paper.pdf)|2019|

|[CelebChild-Test](https://xinntao.github.io/projects/gfpgan)|[Towards Real-World Blind Face Restoration with Generative Facial Prior](https://Arxiv.org/pdf/2101.04061.pdf)|2021|

|[WebPhoto-Test](https://xinntao.github.io/projects/gfpgan)|[Towards Real-World Blind Face Restoration with Generative Facial Prior](https://Arxiv.org/pdf/2101.04061.pdf)|2021|

|[CelebA-Test](https://xinntao.github.io/projects/gfpgan)|[Towards Real-World Blind Face Restoration with Generative Facial Prior](https://Arxiv.org/pdf/2101.04061.pdf)|2021|

|[LFW-Test](https://xinntao.github.io/projects/gfpgan)|[Towards Real-World Blind Face Restoration with Generative Facial Prior](https://Arxiv.org/pdf/2101.04061.pdf)|2021|

|[VFHQ](https://liangbinxie.github.io/projects/vfhq/)|[VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://openaccess.thecvf.com/content/CVPR2022W/NTIRE/papers/Xie_VFHQ_A_High-Quality_Dataset_and_Benchmark_for_Video_Face_Super-Resolution_CVPRW_2022_paper.pdf)|2022|

|[EDFace-Celeb](https://github.com/HDCVLab/EDFace-Celeb-1M)|[EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset](https://Arxiv.org/pdf/2110.05031.pdf)|2022|

|[EDFace-Celeb-1M (BFR128)](https://github.com/bitzpy/Blind-Face-Restoration-Benchmark-Datasets-and-a-Baseline-Model)|[Blind Face Restoration: Benchmark Datasets and a Baseline Model](https://Arxiv.org/pdf/2206.03697.pdf)|2022|

|[EDFace-Celeb-150K (BFR512)](https://github.com/bitzpy/Blind-Face-Restoration-Benchmark-Datasets-and-a-Baseline-Model)|[Blind Face Restoration: Benchmark Datasets and a Baseline Model](https://Arxiv.org/pdf/2206.03697.pdf)|2022|

statistics

![visitors](https://visitor-badge.laobi.icu/badge?page_id=TaoWangzj/Awesome-Face-Restoration)
Ecosyste.ms: Awesome

https://github.com/TaoWangzj/Awesome-Face-Restoration

Awesome Lists containing this project

README

Deep Face Restoartion: Denoise, Super-Resolution, Deblur and Artifact Removal

Deep Face Restoartion: Denoise,
Super-Resolution, Deblur and Artifact Removal
