mlsanityData to 7 Oct 2026

Towards Real-World Blind Face Restoration with Generative Facial Prior

arXiv 2101.04061 ↗First posted 11 Jan 2021cs.CVcited by 347

Not on the map. Why?

Cited by 99 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Thanks to the powerful generative facial prior and delicate designs, our GFP-GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require expensive image-specific optimization at inference. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real-world datasets.

Key facts. Cited by 347 papers in the map (data through 7 Oct 2026). Builds on 59 of its 80 references that are in the map. First posted on arXiv 11 Jan 2021.

Builds on

59 of 80 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2017Mask R-CNNcited by 7,259
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
38 more
  1. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  3. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  8. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  9. 2016Colorful Image Colorizationcited by 1,113
  10. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  11. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  12. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  13. 2019GhostNet: More Features from Cheap Operationscited by 410
  14. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  15. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  16. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  17. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  18. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  19. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  20. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  21. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  22. 2018Non-Local Recurrent Network for Image Restorationcited by 160
  23. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  24. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  25. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  26. 2017Dual Path Networkscited by 119
  27. 2020Blind Face Restoration via Deep Multi-scale Component Dictionariescited by 106
  28. 2020Progressive Semantic-Aware Style Transformation for Blind Face Restorationcited by 99
  29. 2020Bringing Old Photos Back to Lifecited by 95
  30. 2020Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolutioncited by 90
  31. 2018Learning Warped Guidance for Blind Face Restorationcited by 87
  32. 2018Deep Semantic Face Deblurringcited by 80
  33. 2017Generative Face Completioncited by 79
  34. 2017Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesiscited by 75
  35. 2019Progressive Face Super-Resolution via Attention to Facial Landmarkcited by 73
  36. 2020HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishmentcited by 70
  37. 2019LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeupcited by 63
  38. 2019Exemplar Guided Face Image Super-Resolution without Facial Landmarkscited by 57

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 66; 2023: 81; 2024: 80; 2025: 63; 2026: 46.

347 papers.

Sort:

By area:

  1. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  2. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  3. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  4. 2022SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animationcited by 380
  5. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  6. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  7. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  8. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  9. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  10. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
  11. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  12. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
38 more
  1. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  2. 2022VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolutioncited by 174
  3. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  4. 2022Pretraining is All You Need for Image-to-Image Translationcited by 160
  5. 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignmentcited by 143
  6. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  7. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  8. 2022VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wildcited by 106
  9. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  10. 2024Arc2Face: A Foundation Model for ID-Consistent Human Facescited by 101
  11. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
  12. 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 96
  13. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  14. 2024Generalizable and Animatable Gaussian Head Avatarcited by 95
  15. 2023StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generatorcited by 89
  16. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  17. 2024StableAnimator: High-Quality Identity-Preserving Human Image Animationcited by 85
  18. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
  19. 2024GPAvatar: Generalizable and Precise Head Avatar from Image(s)cited by 74
  20. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  21. 2022MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptationcited by 69
  22. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  23. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  24. 2024Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizercited by 64
  25. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  26. 2023Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generationcited by 61
  27. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  28. 2021Towards Vivid and Diverse Image Colorization with Generative Color Priorcited by 55
  29. 2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
  30. 2023NOFA: NeRF-based One-shot Facial Avatar Reconstructioncited by 53
  31. 2023StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Videocited by 52
  32. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  33. 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidancecited by 49
  34. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  35. 2024Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Taskscited by 47
  36. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  37. 2024GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modelingcited by 44
  38. 2022Learning Dual Memory Dictionaries for Blind Face Restorationcited by 40

50 most cited of 347 All 347 (JSON)