mlsanityData to 7 Oct 2026

Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution

arXiv 2203.09195 ↗First posted 17 Mar 2022eess.IV cs.CVcited by 114

Not on the map. Why?

Cited by 54 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Single image super-resolution (SISR) with generative adversarial networks (GAN) has recently attracted increasing attention due to its potentials to generate rich details. However, the training of GAN is unstable, and it often introduces many perceptually unpleasant artifacts along with the generated details. In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts. Based on the observation that the local statistics (e.g., residual variance) of artifact areas are often different from the areas of perceptually friendly details, we develop a framework to discriminate between GAN-generated artifacts and realistic details, and consequently generate an artifact map to regularize and stabilize the model training process. Our proposed locally discriminative learning (LDL) method is simple yet effective, which can be easily plugged in off-the-shelf SISR methods and boost their performance. Experiments demonstrate that LDL outperforms the state-of-the-art GAN based SISR methods, achieving not only higher reconstruction accuracy but also superior perceptual quality on both synthetic and real-world datasets. Codes and models are available at https://github.com/csjliang/LDL.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

35 of 49 references.

References · 35

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  7. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  8. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  9. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  10. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  11. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  12. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
23 more
  1. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  2. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  3. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  4. 2017The Perception-Distortion Tradeoffcited by 582
  5. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  6. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  7. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  8. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  9. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  10. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  11. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  12. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  13. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  14. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  15. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  16. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 158
  17. 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
  18. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  19. 2021Fourier Space Losses for Efficient Perceptual Image Super-Resolutioncited by 72
  20. 2020Learning A Single Network for Scale-Arbitrary Super-Resolutioncited by 65
  21. 2019Densely Residual Laplacian Super-Resolutioncited by 57
  22. 2019Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discriminationcited by 32
  23. 2019SROBB: Targeted Perceptual Loss for Single Image Super-Resolutioncited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 18; 2024: 32; 2025: 44; 2026: 18.

114 papers.

Sort:

By area:

  1. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  2. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  3. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  4. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  5. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  6. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  7. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  8. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  9. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 64
  10. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  11. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  12. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
38 more
  1. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  2. 2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
  3. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  4. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34
  5. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 31
  6. 2024SeD: Semantic-Aware Discriminator for Image Super-Resolutioncited by 26
  7. 2024LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Modelscited by 22
  8. 2022Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimationcited by 21
  9. 2025Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolutioncited by 21
  10. 2025DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolutioncited by 21
  11. 2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
  12. 2023Human Guided Ground-truth Generation for Realistic Image Super-resolutioncited by 20
  13. 2024Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminatorcited by 18
  14. 2024Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Losscited by 17
  15. 2024Beyond Pixels: Text Enhances Generalization in Real-World Image Restorationcited by 17
  16. 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generationcited by 17
  17. 2024Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifactscited by 16
  18. 2023Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolutioncited by 15
  19. 2025The Power of Context: How Multimodality Improves Image Super-Resolutioncited by 15
  20. 2023Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformerscited by 13
  21. 2024Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEscited by 13
  22. 2023DREAM: Diffusion Rectification and Estimation-Adaptive Modelscited by 12
  23. 2023Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspectivecited by 11
  24. 2024Disentangled Motion Modeling for Video Frame Interpolationcited by 11
  25. 2024SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolutioncited by 10
  26. 2024DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolutioncited by 9
  27. 2023On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvementcited by 8
  28. 2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
  29. 2024Boosting Flow-based Generative Super-Resolution Models via Learned Priorcited by 7
  30. 2024CasSR: Activating Image Power for Real-World Image Super-Resolutioncited by 7
  31. 2025Augmenting Perceptual Super-Resolution via Image Quality Predictorscited by 7
  32. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolutioncited by 7
  33. 2025Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoderscited by 6
  34. 2025Time-Aware One Step Diffusion Network for Real-World Image Super-Resolutioncited by 6
  35. 2026Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensationcited by 6
  36. 2023L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priorscited by 5
  37. 2025One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillationcited by 5
  38. 2025Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolutioncited by 5

50 most cited of 114 All 114 (JSON)