mlsanityData to 14 Oct 2026

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

arXiv 1511.04587 ↗First posted 14 Nov 2015cs.CV cs.LGcited by 903

Not on the map. Why?

Cited by 76 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a highly accurate single-image super-resolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification citesimonyan2015very. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters many times in a deep network structure, contextual information over large image regions is exploited in an efficient way. With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure. We learn residuals only and use extremely high learning rates (104 times higher than SRCNN citedong2015image) enabled by adjustable gradient clipping. Our proposed method performs better than existing methods in accuracy and visual improvements in our results are easily noticeable.

Key facts. Cited by 903 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 2; 2021: 205; 2022: 215; 2023: 146; 2024: 146; 2025: 125; 2026: 64.

903 papers.

Sort:

By area:

  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  3. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  4. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  5. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  6. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  7. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 352
  8. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 255
  9. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 238
  10. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  11. 2022VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolutioncited by 176
  12. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
38 more
  1. 2021Transformer for Single Image Super-Resolutioncited by 150
  2. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  3. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  4. 2021Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embeddingcited by 134
  5. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  6. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  7. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  8. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 100
  9. 2024MambaIRv2: Attentive State Space Restorationcited by 94
  10. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  11. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  12. 2021LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyondcited by 88
  13. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 87
  14. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  15. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  16. 2021Deep Burst Super-Resolutioncited by 83
  17. 2021ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristiccited by 81
  18. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 80
  19. 2022NAFSSR: Stereo Image Super-Resolution Using NAFNetcited by 76
  20. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  21. 2021Fourier Space Losses for Efficient Perceptual Image Super-Resolutioncited by 73
  22. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  23. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 73
  24. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 70
  25. 2021Robust Reference-based Super-Resolution via C2-Matchingcited by 69
  26. 2022SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolutioncited by 68
  27. 2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 66
  28. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 66
  29. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  30. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  31. 2024Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionarycited by 64
  32. 2023Omni Aggregation Networks for Lightweight Image Super-Resolutioncited by 62
  33. 2021UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolutioncited by 57
  34. 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 57
  35. 2023EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolutioncited by 56
  36. 2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
  37. 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolutioncited by 52
  38. 2021NTIRE 2021 Challenge on Image Deblurringcited by 50

50 most cited of 903 All 903 (JSON)