mlsanityData to 7 Oct 2026

Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model

arXiv 1904.00523 ↗First posted 1 Apr 2019cs.CVcited by 400

Not on the map. Why?

Cited by 129 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic downsampling) to their high-resolution (HR) counterparts. However, the degradations in real-world LR images are far more complicated. As a consequence, the SISR models trained on simulated data become less effective when applied to practical scenarios. In this paper, we build a real-world super-resolution (RealSR) dataset where paired LR-HR images on the same scene are captured by adjusting the focal length of a digital camera. An image registration algorithm is developed to progressively align the image pairs at different resolutions. Considering that the degradation kernels are naturally non-uniform in our dataset, we present a Laplacian pyramid based kernel prediction network (LP-KPN), which efficiently learns per-pixel kernels to recover the HR image. Our extensive experiments demonstrate that SISR models trained on our RealSR dataset deliver better visual quality with sharper edges and finer textures on real-world scenes than those trained on simulated datasets. Though our RealSR dataset is built by using only two cameras (Canon 5D3 and Nikon D810), the trained model generalizes well to other camera devices such as Sony a7II and mobile phones.

Key facts. Cited by 400 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 40; 2022: 52; 2023: 54; 2024: 65; 2025: 105; 2026: 83.

400 papers.

Sort:

By area:

  1. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  2. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  3. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  4. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  5. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  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. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  9. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  10. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  11. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  12. 2021Transformer for Single Image Super-Resolutioncited by 150
38 more
  1. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  2. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  3. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  4. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  5. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  6. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  7. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  8. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  9. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  10. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  11. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  12. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  13. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  14. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priorscited by 64
  15. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 64
  16. 2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
  17. 2024Towards Realistic Data Generation for Real-World Super-Resolutioncited by 56
  18. 2022Realistic Blur Synthesis for Learning Image Deblurringcited by 51
  19. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  20. 2021NTIRE 2021 Challenge on Image Deblurringcited by 49
  21. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  22. 2023Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wildcited by 46
  23. 2021Learning to Resize Images for Computer Vision Taskscited by 45
  24. 2023Boosting Latent Diffusion with Flow Matchingcited by 44
  25. 2021Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervisioncited by 43
  26. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  27. 2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
  28. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  29. 2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
  30. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  31. 2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
  32. 2025Harnessing Diffusion-Yielded Score Priors for Image Restorationcited by 34
  33. 2021Dual-Camera Super-Resolution with Aligned Attention Modulescited by 33
  34. 2022MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolutioncited by 33
  35. 2024PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructionscited by 31
  36. 2021DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flowscited by 30
  37. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  38. 2025Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Modelcited by 29

50 most cited of 400 All 400 (JSON)