mlsanityData to 14 Oct 2026

Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance

arXiv 2510.21590 ↗First posted 24 Oct 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Current image super-resolution methods show strong performance on natural images but distort text, creating a fundamental trade-off between image quality and textual readability. To address this, we introduce TIGER (Text-Image Guided supEr-Resolution), a novel two-stage framework that breaks this trade-off through a "text-first, image-later" paradigm. TIGER explicitly decouples glyph restoration from image enhancement: it first reconstructs precise text structures and uses them to guide full-image super-resolution. This ensures high fidelity and readability. To support comprehensive training and evaluation, we present the UZ-ST (UltraZoom-Scene Text) dataset, the first Chinese scene text dataset with extreme zoom. Extensive experiments show TIGER achieves state-of-the-art performance, enhancing readability and image quality.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 44 of its 58 references that are in the map. First posted on arXiv 24 Oct 2025.

Builds on

44 of 58 references.

References · 44

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  9. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  10. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  11. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  12. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
32 more
  1. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  2. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  3. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  4. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  5. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  6. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  7. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 254
  8. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 246
  9. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 238
  10. 2023AnyText: Multilingual Visual Text Generation And Editingcited by 170
  11. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 106
  12. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 87
  13. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 65
  14. 2020Scene Text Image Super-Resolution in the Wildcited by 63
  15. 2021Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Studycited by 53
  16. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 53
  17. 2024Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Drivingcited by 46
  18. 2023ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bankcited by 36
  19. 2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
  20. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  21. 2022PreSTU: Pre-Training for Scene-Text Understandingcited by 27
  22. 2019TextSR: Content-Aware Text Super-Resolution Guided by Recognitioncited by 26
  23. 2023Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligningcited by 26
  24. 2023Diffusion-based Blind Text Image Super-Resolutioncited by 25
  25. 2023Learning Generative Structure Prior for Blind Text Image Super-resolutioncited by 24
  26. 2024Effective Diffusion Transformer Architecture for Image Super-Resolutioncited by 21
  27. 2015Boosting Optical Character Recognition: A Super-Resolution Approachcited by 19
  28. 2023A Benchmark for Chinese-English Scene Text Image Super-resolutioncited by 17
  29. 2022Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancementcited by 16
  30. 2025RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extractioncited by 9
  31. 2025Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoderscited by 7
  32. 2022A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Datacited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Unified Diffusion Transformer for High-fidelity Text-Aware Image Restorationcited by 3
  2. 2026Beyond Readability: Evaluating Task Information Recoverabilitycited by 0
  3. 2026TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolutioncited by 0