mlsanityData to 7 Oct 2026

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

arXiv 2311.16518 ↗First posted 27 Nov 2023cs.CVcited by 311

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Owe to the powerful generative priors, the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However, as a consequence of the heavy quality degradation of input low-resolution (LR) images, the destruction of local structures can lead to ambiguous image semantics. As a result, the content of reproduced high-resolution image may have semantic errors, deteriorating the super-resolution performance. To address this issue, we present a semantics-aware approach to better preserve the semantic fidelity of generative real-world image super-resolution. First, we train a degradation-aware prompt extractor, which can generate accurate soft and hard semantic prompts even under strong degradation. The hard semantic prompts refer to the image tags, aiming to enhance the local perception ability of the T2I model, while the soft semantic prompts compensate for the hard ones to provide additional representation information. These semantic prompts encourage the T2I model to generate detailed and semantically accurate results. Furthermore, during the inference process, we integrate the LR images into the initial sampling noise to mitigate the diffusion model's tendency to generate excessive random details. The experiments show that our method can reproduce more realistic image details and hold better the semantics. The source code of our method can be found at https://github.com/cswry/SeeSR.

Key facts. Cited by 311 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 66 of its 85 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

66 of 85 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior29 Aug
  2. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization28 Aug
  3. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting23 Jul
  4. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  5. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  6. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2017Mask R-CNNcited by 7,259
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
38 more
  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  9. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  10. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  11. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  13. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  14. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  15. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  16. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  17. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  18. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  19. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  20. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  21. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  22. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  23. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  24. 2020Pre-Trained Image Processing Transformercited by 891
  25. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  26. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  27. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  28. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  29. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  30. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  31. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  32. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  33. 2023Recognize Anything: A Strong Image Tagging Modelcited by 305
  34. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  35. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  36. 2023A Simple Framework for Open-Vocabulary Segmentation and Detectioncited by 197
  37. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  38. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 68; 2025: 136; 2026: 105.

311 papers.

Sort:

By area:

  1. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  2. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  3. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  4. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  5. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  6. 2025FlowDPS: Flow-Driven Posterior Sampling for Inverse Problemscited by 65
  7. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  8. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 64
  9. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  10. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  11. 2024Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single Viewcited by 59
  12. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
38 more
  1. 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Modelscited by 51
  2. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  3. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  4. 2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
  5. 2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Modelscited by 41
  6. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  7. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  8. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34
  9. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  10. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 31
  11. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  12. 2024QMambaBSR: Burst Image Super-Resolution with Query State Space Modelcited by 27
  13. 2024UniVS: Unified and Universal Video Segmentation with Prompts as Queriescited by 26
  14. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 25
  15. 2023SPIRE: Semantic Prompt-Driven Image Restorationcited by 24
  16. 2025Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Modelscited by 24
  17. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  18. 2025Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolutioncited by 21
  19. 2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
  20. 2024Effective Diffusion Transformer Architecture for Image Super-Resolutioncited by 20
  21. 2024Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Modelscited by 19
  22. 2024Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restorationcited by 19
  23. 2025Multi-Agent Image Restorationcited by 19
  24. 2024Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restorationcited by 18
  25. 2024Binarized Diffusion Model for Image Super-Resolutioncited by 18
  26. 2024Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminatorcited by 18
  27. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restorationcited by 18
  28. 2024Beyond Pixels: Text Enhances Generalization in Real-World Image Restorationcited by 17
  29. 2025Solving Inverse Problems with FLAIRcited by 16
  30. 2023Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolutioncited by 15
  31. 2024Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restorationcited by 15
  32. 2024ReFIR: Grounding Large Restoration Models with Retrieval Augmentationcited by 15
  33. 2025The Power of Context: How Multimodality Improves Image Super-Resolutioncited by 15
  34. 2025Dual Prompting Image Restoration with Diffusion Transformerscited by 15
  35. 2024DiffRetouch: Using Diffusion to Retouch on the Shoulder of Expertscited by 14
  36. 2024MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMscited by 14
  37. 2025NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Resultscited by 14
  38. 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolutioncited by 14

50 most cited of 311 All 311 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Preserve More Details: Mitigating Content Drift in Real-World Image Super-Resolution
  2. 2024Semantic Segmentation Prior for Diffusion-Based Real-World Super-Resolution
  3. 2024Text-guided Explorable Image Super-resolution
  4. 2024Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors
  5. 2025Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution
  6. 2023Image Super-Resolution with Text Prompt Diffusion
  7. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
  8. 2026Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention