mlsanityData to 14 Oct 2026

Scene Text Image Super-resolution based on Text-conditional Diffusion Models

arXiv 2311.09759 ↗First posted 16 Nov 2023cs.CVcited by 15

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

Abstract (arXiv)

Scene Text Image Super-resolution (STISR) has recently achieved great success as a preprocessing method for scene text recognition. STISR aims to transform blurred and noisy low-resolution (LR) text images in real-world settings into clear high-resolution (HR) text images suitable for scene text recognition. In this study, we leverage text-conditional diffusion models (DMs), known for their impressive text-to-image synthesis capabilities, for STISR tasks. Our experimental results revealed that text-conditional DMs notably surpass existing STISR methods. Especially when texts from LR text images are given as input, the text-conditional DMs are able to produce superior quality super-resolution text images. Utilizing this capability, we propose a novel framework for synthesizing LR-HR paired text image datasets. This framework consists of three specialized text-conditional DMs, each dedicated to text image synthesis, super-resolution, and image degradation. These three modules are vital for synthesizing distinct LR and HR paired images, which are more suitable for training STISR methods. Our experiments confirmed that these synthesized image pairs significantly enhance the performance of STISR methods in the TextZoom evaluation.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 47 of its 66 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

47 of 66 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
35 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  2. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  4. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  5. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  7. 2022Diffusion Models in Vision: A Surveycited by 1,015
  8. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  10. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  11. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  12. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  13. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 499
  14. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  15. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  16. 2016COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Imagescited by 236
  17. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  18. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  19. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 149
  20. 2019ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)cited by 147
  21. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 139
  22. 2019ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboardcited by 128
  23. 2019ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVTcited by 122
  24. 2017ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)cited by 105
  25. 2020Unpaired Image Super-Resolution using Pseudo-Supervisioncited by 67
  26. 2020Scene Text Image Super-Resolution in the Wildcited by 63
  27. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
  28. 2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
  29. 2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
  30. 2022Text2Human: Text-Driven Controllable Human Image Generationcited by 31
  31. 2019A Multi-Object Rectified Attention Network for Scene Text Recognitioncited by 30
  32. 2021Text Gestalt: Stroke-Aware Scene Text Image Super-Resolutioncited by 28
  33. 2019TextSR: Content-Aware Text Super-Resolution Guided by Recognitioncited by 26
  34. 2022C3-STISR: Scene Text Image Super-resolution with Triple Cluescited by 26
  35. 2015Boosting Optical Character Recognition: A Super-Resolution Approachcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 8; 2026: 2.

15 papers.

Sort:

By area:

  1. 2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 19
  2. 2024FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Modelscited by 13
  3. 2024Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processingcited by 8
  4. 2025Dual-domain Modulation Network for Lightweight Image Super-Resolutioncited by 8
  5. 2023PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolutioncited by 4
  6. 2024Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessmentcited by 4
  7. 2025Enhanced Generative Structure Prior for Chinese Text Image Super-resolutioncited by 3
  8. 2025Unified Diffusion Transformer for High-fidelity Text-Aware Image Restorationcited by 3
  9. 2025NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Priorcited by 1
  10. 2025TextSR: Diffusion Super-Resolution with Multilingual OCR Guidancecited by 1
  11. 2026DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolutioncited by 1
  12. 2024Text Image Generation for Low-Resource Languages with Dual Translation Learningcited by 0
3 more
  1. 2025CharDiff-LP: A Diffusion Model with Character-Level Guidance for License Plate Image Restorationcited by 0
  2. 2025GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?cited by 0
  3. 2026TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution
  2. 2023TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution
  3. 2025Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders
  4. 2026Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolution
  5. 2024TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition
  6. 2025Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarios
  7. 2026TEXTS-Diff: TEXTS-Aware Diffusion Model for Real-World Text Image Super-Resolution
  8. 2023Diffusion-based Blind Text Image Super-Resolution