mlsanityData to 7 Oct 2026

Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

arXiv 2401.13627 ↗First posted 24 Jan 2024cs.CVcited by 281

Not on the map. Why?

Cited by 143 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-modal techniques and advanced generative prior, SUPIR marks a significant advance in intelligent and realistic image restoration. As a pivotal catalyst within SUPIR, model scaling dramatically enhances its capabilities and demonstrates new potential for image restoration. We collect a dataset comprising 20 million high-resolution, high-quality images for model training, each enriched with descriptive text annotations. SUPIR provides the capability to restore images guided by textual prompts, broadening its application scope and potential. Moreover, we introduce negative-quality prompts to further improve perceptual quality. We also develop a restoration-guided sampling method to suppress the fidelity issue encountered in generative-based restoration. Experiments demonstrate SUPIR's exceptional restoration effects and its novel capacity to manipulate restoration through textual prompts.

Key facts. Cited by 281 papers in the map (data through 7 Oct 2026). Builds on 87 of its 103 references that are in the map. First posted on arXiv 24 Jan 2024.

Builds on

87 of 103 references.

References · 87

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2023Segment Anythingcited by 8,158
  11. 2023Visual Instruction Tuningcited by 7,792
  12. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
38 more
  1. 2020Scaling Laws for Neural Language Modelscited by 6,411
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  6. 2017Neural Discrete Representation Learningcited by 4,650
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  13. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  14. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  15. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  16. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  17. 2018Group Normalizationcited by 1,514
  18. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  19. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  20. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  21. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  22. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  23. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  24. 2022Denoising Diffusion Restoration Modelscited by 951
  25. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  26. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  27. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  28. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  29. 2017The Perception-Distortion Tradeoffcited by 582
  30. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  31. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  32. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  33. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  34. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  35. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  36. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  37. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  38. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 74; 2025: 120; 2026: 87.

281 papers.

Sort:

By area:

  1. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  2. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  3. 2024ControlNeXt: Powerful and Efficient Control for Image and Video Generationcited by 158
  4. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  5. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  6. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  7. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  8. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  9. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 64
  10. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priorscited by 64
  11. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 64
  12. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
38 more
  1. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  2. 2024Towards Realistic Data Generation for Real-World Super-Resolutioncited by 56
  3. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  4. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  5. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  6. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  7. 2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Modelscited by 41
  8. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  9. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  10. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  11. 2025VisualCloze: A Universal Image Generation Framework via Visual In-Context Learningcited by 39
  12. 2024FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restorationcited by 37
  13. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34
  14. 2025FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generationcited by 32
  15. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 31
  16. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
  17. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 25
  18. 2024CU-Mamba: Selective State Space Models with Channel Learning for Image Restorationcited by 24
  19. 2025Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Modelscited by 24
  20. 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoisingcited by 22
  21. 2024OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offscited by 22
  22. 2025Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolutioncited by 21
  23. 2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
  24. 2024PromptCIR: Blind Compressed Image Restoration with Prompt Learningcited by 20
  25. 2024Effective Diffusion Transformer Architecture for Image Super-Resolutioncited by 20
  26. 2025UltraFusion: Ultra High Dynamic Imaging using Exposure Fusioncited by 20
  27. 2024Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Modelscited by 19
  28. 2025Multi-Agent Image Restorationcited by 19
  29. 2025UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texturecited by 19
  30. 2024Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restorationcited by 18
  31. 2024Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminatorcited by 18
  32. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restorationcited by 18
  33. 2024Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Losscited by 17
  34. 2024Beyond Pixels: Text Enhances Generalization in Real-World Image Restorationcited by 17
  35. 2024Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restorationcited by 15
  36. 2024MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restorationcited by 15
  37. 2024ReFIR: Grounding Large Restoration Models with Retrieval Augmentationcited by 15
  38. 2024FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Samplingcited by 15

50 most cited of 281 All 281 (JSON)