mlsanityData to 7 Oct 2026

Towards Robust Blind Face Restoration with Codebook Lookup Transformer

arXiv 2206.11253 ↗First posted 22 Jun 2022cs.CVcited by 230

Not on the map. Why?

Cited by 84 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Blind face restoration is a highly ill-posed problem that often requires auxiliary guidance to 1) improve the mapping from degraded inputs to desired outputs, or 2) complement high-quality details lost in the inputs. In this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces. Under this paradigm, we propose a Transformer-based prediction network, named CodeFormer, to model the global composition and context of the low-quality faces for code prediction, enabling the discovery of natural faces that closely approximate the target faces even when the inputs are severely degraded. To enhance the adaptiveness for different degradation, we also propose a controllable feature transformation module that allows a flexible trade-off between fidelity and quality. Thanks to the expressive codebook prior and global modeling, CodeFormer outperforms the state of the arts in both quality and fidelity, showing superior robustness to degradation. Extensive experimental results on synthetic and real-world datasets verify the effectiveness of our method.

Key facts. Cited by 230 papers in the map (data through 7 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 22 Jun 2022.

Builds on

33 of 62 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  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. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017Neural Discrete Representation Learningcited by 4,650
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  12. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
21 more
  1. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  2. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  3. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  4. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  5. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  6. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  7. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  8. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  9. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  10. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  11. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  12. 2020Blind Face Restoration via Deep Multi-scale Component Dictionariescited by 106
  13. 2020Progressive Semantic-Aware Style Transformation for Blind Face Restorationcited by 99
  14. 2020Cross-Scale Internal Graph Neural Network for Image Super-Resolutioncited by 94
  15. 2018Learning Warped Guidance for Blind Face Restorationcited by 87
  16. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  17. 2018Deep Semantic Face Deblurringcited by 80
  18. 2020HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishmentcited by 70
  19. 2021Image Inpainting via Conditional Texture and Structure Dual Generationcited by 66
  20. 2019Exemplar Guided Face Image Super-Resolution without Facial Landmarkscited by 57
  21. 2020Face Super-Resolution Guided by 3D Facial Priorscited by 38

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 44; 2024: 70; 2025: 70; 2026: 41.

230 papers.

Sort:

By area:

  1. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  2. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  3. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  4. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  5. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  6. 2023CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Priorcited by 183
  7. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  8. 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 96
  9. 2024Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animationcited by 95
  10. 2024StableAnimator: High-Quality Identity-Preserving Human Image Animationcited by 85
  11. 2023DR2: Diffusion-based Robust Degradation Remover for Blind Face Restorationcited by 79
  12. 2023RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priorscited by 73
38 more
  1. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  2. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  3. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  4. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  5. 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidancecited by 49
  6. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  7. 2024FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantizationcited by 39
  8. 2024SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAEcited by 38
  9. 2023RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairscited by 33
  10. 2024GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrievalcited by 33
  11. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  12. 2024Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restorationcited by 32
  13. 2022Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesiscited by 31
  14. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 31
  15. 2025ARTalk: Speech-Driven 3D Head Animation via Autoregressive Modelcited by 28
  16. 2022Face Generation and Editing with StyleGAN: A Surveycited by 27
  17. 2023Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Modelscited by 26
  18. 2023Transformer-VQ: Linear-Time Transformers via Vector Quantizationcited by 26
  19. 2025Human Motion Video Generation: A Surveycited by 25
  20. 2023SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistencycited by 24
  21. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
  22. 2023Dual Associated Encoder for Face Restorationcited by 23
  23. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  24. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
  25. 2023Towards Real-World Blind Face Restoration with Generative Diffusion Priorcited by 21
  26. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  27. 2023MagiCapture: High-Resolution Multi-Concept Portrait Customizationcited by 20
  28. 2024WaveFace: Authentic Face Restoration with Efficient Frequency Recoverycited by 20
  29. 2024Effective Diffusion Transformer Architecture for Image Super-Resolutioncited by 20
  30. 2024Upsample Guidance: Scale Up Diffusion Models without Trainingcited by 19
  31. 2023Towards Authentic Face Restoration with Iterative Diffusion Models and Beyondcited by 18
  32. 2023Survey on Deep Face Restoration: From Non-blind to Blind and Beyondcited by 18
  33. 2022Deep Face Restoration: A Surveycited by 17
  34. 2023TextIR: A Simple Framework for Text-based Editable Image Restorationcited by 17
  35. 2023Federated Prompt Learning for Weather Foundation Models on Devicescited by 17
  36. 2023Deep Equilibrium Diffusion Restoration with Parallel Samplingcited by 17
  37. 2024One Step Diffusion-based Super-Resolution with Time-Aware Distillationcited by 17
  38. 2025Iterative Predictor-Critic Code Decoding for Real-World Image Dehazingcited by 16

50 most cited of 230 All 230 (JSON)