mlsanityData to 7 Oct 2026

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

arXiv 2103.14006 ↗First posted 25 Mar 2021eess.IV cs.CVcited by 524

Not on the map. Why?

Cited by 179 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

It is widely acknowledged that single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. Although several degradation models take additional factors into consideration, such as blur, they are still not effective enough to cover the diverse degradations of real images. To address this issue, this paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations. Specifically, the blur is approximated by two convolutions with isotropic and anisotropic Gaussian kernels; the downsampling is randomly chosen from nearest, bilinear and bicubic interpolations; the noise is synthesized by adding Gaussian noise with different noise levels, adopting JPEG compression with different quality factors, and generating processed camera sensor noise via reverse-forward camera image signal processing (ISP) pipeline model and RAW image noise model. To verify the effectiveness of the new degradation model, we have trained a deep blind ESRGAN super-resolver and then applied it to super-resolve both synthetic and real images with diverse degradations. The experimental results demonstrate that the new degradation model can help to significantly improve the practicability of deep super-resolvers, thus providing a powerful alternative solution for real SISR applications.

Key facts. Cited by 524 papers in the map (data through 7 Oct 2026). Builds on 37 of its 68 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

37 of 68 references.

References · 37

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  10. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  11. 2017The Perception-Distortion Tradeoffcited by 582
  12. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
25 more
  1. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  2. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  3. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  4. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  5. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  6. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  7. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  8. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  9. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
  10. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  11. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  12. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  13. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  14. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  15. 2019Blind Super-Resolution Kernel Estimation using an Internal-GANcited by 175
  16. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  17. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  18. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
  19. 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
  20. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  21. 2019Frequency Separation for Real-World Super-Resolutioncited by 115
  22. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  23. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  24. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  25. 2020AIM 2020 Challenge on Real Image Super-Resolution: Methods and Resultscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 58; 2023: 88; 2024: 120; 2025: 137; 2026: 99.

524 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  5. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  7. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  8. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  9. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  10. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  11. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  12. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
38 more
  1. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  2. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  3. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  4. 2022VRT: A Video Restoration Transformercited by 219
  5. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  6. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  7. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  8. 2022Pretraining is All You Need for Image-to-Image Translationcited by 160
  9. 2024ControlNeXt: Powerful and Efficient Control for Image and Video Generationcited by 158
  10. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  11. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  12. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  13. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 113
  14. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  15. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  16. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 105
  17. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
  18. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  19. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  20. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  21. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  22. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  23. 2023ARNIQA: Learning Distortion Manifold for Image Quality Assessmentcited by 87
  24. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 85
  25. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  26. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  27. 2021Towards Flexible Blind JPEG Artifacts Removalcited by 76
  28. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  29. 2023VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generationcited by 74
  30. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  31. 2023RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priorscited by 73
  32. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
  33. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  34. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  35. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  36. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  37. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  38. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 64

50 most cited of 524 All 524 (JSON)