mlsanityData to 14 Oct 2026

Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration

arXiv 2306.06513 ↗First posted 10 Jun 2023cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Recent work on discrete generative priors, in the form of codebooks, has shown exciting performance for image reconstruction and restoration, as the discrete prior space spanned by the codebooks increases the robustness against diverse image degradations. Nevertheless, these methods require separate training of codebooks for different image categories, which limits their use to specific image categories only (e.g. face, architecture, etc.), and fail to handle arbitrary natural images. In this paper, we propose AdaCode for learning image-adaptive codebooks for class-agnostic image restoration. Instead of learning a single codebook for each image category, we learn a set of basis codebooks. For a given input image, AdaCode learns a weight map with which we compute a weighted combination of these basis codebooks for adaptive image restoration. Intuitively, AdaCode is a more flexible and expressive discrete generative prior than previous work. Experimental results demonstrate that AdaCode achieves state-of-the-art performance on image reconstruction and restoration tasks, including image super-resolution and inpainting.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 10 Jun 2023.

Builds on

49 of 64 references.

References · 49

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  9. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  10. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  11. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  12. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
37 more
  1. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  2. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  3. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  4. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  5. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  6. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  7. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 371
  8. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  9. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 246
  10. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
  11. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  12. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 218
  13. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  14. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  15. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 163
  16. 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
  17. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  18. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  19. 2019StructureFlow: Image Inpainting via Structure-aware Appearance Flowcited by 118
  20. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  21. 2020Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizationscited by 102
  22. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 100
  23. 2019Learning Pyramid-Context Encoder Network for High-Quality Image Inpaintingcited by 94
  24. 2019Foreground-aware Image Inpaintingcited by 90
  25. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  26. 2022Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encodingcited by 83
  27. 2018Image Inpainting via Generative Multi-column Convolutional Neural Networkscited by 81
  28. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  29. 2022AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancementcited by 70
  30. 2021Image Inpainting via Conditional Texture and Structure Dual Generationcited by 66
  31. 2017UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognitioncited by 62
  32. 2018SPG-Net: Segmentation Prediction and Guidance Network for Image Inpaintingcited by 58
  33. 2022SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancementcited by 50
  34. 2022Reduce Information Loss in Transformers for Pluralistic Image Inpaintingcited by 36
  35. 20224D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancementcited by 34
  36. 2018Learning Hierarchical Semantic Image Manipulation through Structured Representationscited by 27
  37. 2022KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolutioncited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 5; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 100
  2. 2024Restoring Images in Adverse Weather Conditions via Histogram Transformercited by 73
  3. 2025Learned Image Compression with Dictionary-based Entropy Modelcited by 30
  4. 2024HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compressioncited by 14
  5. 2025TVC: Tokenized Video Compression with Ultra-Low Bit Ratecited by 7
  6. 2023Neural Image Compression Using Masked Sparse Visual Representationcited by 5
  7. 2024Monocular Identity-Conditioned Facial Reflectance Reconstructioncited by 5
  8. 2025Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Textcited by 4
  9. 2025Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolutioncited by 3
  10. 2024GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Contentcited by 2
  11. 2025mathttM3VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creationcited by 0
  12. 2026LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantizationcited by 0
2 more
  1. 2026Enhancing Underwater Images via Adaptive Semantic-aware Codebook Learningcited by 0
  2. 2026Adaptive Fused Prior Transfer for Controllable Generative Image Compressioncited by 0