mlsanityData to 7 Oct 2026

Towards Realistic Data Generation for Real-World Super-Resolution

arXiv 2406.07255 ↗First posted 11 Jun 2024cs.CV eess.IVcited by 56

Not on the map. Why?

Abstract (arXiv)

Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts have either manually simulated intricate physical-based degradations or utilized learning-based techniques, yet these approaches remain inadequate for producing large-scale, realistic, and diverse data simultaneously. In this paper, we introduce a novel Realistic Decoupled Data Generator (RealDGen), an unsupervised learning data generation framework designed for real-world super-resolution. We meticulously develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model to create realistic low-resolution images from unpaired real LR and HR images. Extensive experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations, significantly advancing the performance of popular SR models on various real-world benchmarks.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 48 of its 65 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

48 of 65 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  7. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  8. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  9. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  10. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  11. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  12. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
36 more
  1. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  2. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  3. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  4. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  5. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  6. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  7. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  8. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  9. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  10. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  11. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  12. 2023DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Modelscited by 122
  13. 2019Frequency Separation for Real-World Super-Resolutioncited by 115
  14. 2018To learn image super-resolution, use a GAN to learn how to do image degradation firstcited by 94
  15. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  16. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  17. 2022Generating High Fidelity Data from Low-density Regions using Diffusion Modelscited by 78
  18. 2020Unpaired Image Super-Resolution using Pseudo-Supervisioncited by 67
  19. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  20. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  21. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  22. 2019Camera Lens Super-Resolutioncited by 56
  23. 2018Task-Driven Super Resolution: Object Detection in Low-resolution Imagescited by 52
  24. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  25. 2019AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 34
  26. 2022MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolutioncited by 33
  27. 2021DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flowscited by 30
  28. 2021Best-Buddy GANs for Highly Detailed Image Super-Resolutioncited by 30
  29. 2023Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolutioncited by 21
  30. 2023Human Guided Ground-truth Generation for Realistic Image Super-resolutioncited by 20
  31. 2024Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learningcited by 19
  32. 2024Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Surveycited by 19
  33. 2022Evaluating the Generalization Ability of Super-Resolution Networkscited by 18
  34. 2022From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolutioncited by 15
  35. 2023SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolutioncited by 12
  36. 2023Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approachcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 29; 2026: 17.

56 papers.

Sort:

By area:

  1. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  2. 2025Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modelingcited by 47
  3. 2025Towards Universal Modal Tracking with Online Dense Temporal Token Learningcited by 30
  4. 2024QMambaBSR: Burst Image Super-Resolution with Query State Space Modelcited by 27
  5. 2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restorationcited by 27
  6. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 25
  7. 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detectioncited by 24
  8. 2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
  9. 2024Multi-Reward as Condition for Instruction-based Image Editingcited by 20
  10. 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancementcited by 17
  11. 2025Data-free Knowledge Distillation with Diffusion Modelscited by 16
  12. 2025Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesiscited by 13
38 more
  1. 2025RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditionscited by 13
  2. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 13
  3. 2024S3Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Modelcited by 12
  4. 2024FC3DNet: A Fully Connected Encoder-Decoder for Efficient Demoir'eingcited by 11
  5. 2024Progressive Compositionality in Text-to-Image Generative Modelscited by 11
  6. 2025Intra and Inter Parser-Prompted Transformers for Effective Image Restorationcited by 10
  7. 2024DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolutioncited by 9
  8. 2025Dual-domain Modulation Network for Lightweight Image Super-Resolutioncited by 8
  9. 2026Fast Image Super-Resolution via Consistency Rectified Flowcited by 7
  10. 2025Eevee: Towards Close-up High-resolution Video-based Virtual Try-oncited by 5
  11. 2026Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separationcited by 5
  12. 2025Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generationcited by 4
  13. 2025Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignmentcited by 4
  14. 2025Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidancecited by 4
  15. 2025DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Modelcited by 3
  16. 2026GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolutioncited by 3
  17. 2025SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolutioncited by 2
  18. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 2
  19. 2025Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removalcited by 2
  20. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarkingcited by 2
  21. 2026EventGait: Towards Robust Gait Recognition with Event Streamscited by 2
  22. 2026Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Datasetcited by 2
  23. 2024Joint multi-dimensional dynamic attention and transformer for general image restorationcited by 1
  24. 2025FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolutioncited by 1
  25. 2025Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Surveycited by 1
  26. 2026Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolutioncited by 1
  27. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offscited by 1
  28. 2026Learning to Track Instance from Single Nature Language Descriptioncited by 1
  29. 2024Adaptive Frequency Enhancement Network for Single Image Derainingcited by 0
  30. 2025Iterative Optimal Attention and Local Model for Single Image Rain Streak Removalcited by 0
  31. 2025Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patternscited by 0
  32. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  33. 2025SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Imagescited by 0
  34. 2025Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustnesscited by 0
  35. 2025Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generationcited by 0
  36. 2025DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Derainingcited by 0
  37. 2025Transformer-Progressive Mamba Network for Lightweight Image Super-Resolutioncited by 0
  38. 2026Vision-Language Controlled Deep Unfolding for Joint Medical Image Restoration and Segmentationcited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
  2. 2024DeeDSR: Towards Real-World Image Super-Resolution via Degradation-Aware Stable Diffusion
  3. 2025Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling
  4. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step
  5. 2025Realism Control One-step Diffusion for Real-World Image Super-Resolution
  6. 2026Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
  7. 2026Degradation-Aware and Structure-Preserving Diffusion for Real-World Image Super-Resolution
  8. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolution