mlsanityData to 14 Oct 2026

Text Prior Guided Scene Text Image Super-resolution

arXiv 2106.15368 ↗First posted 29 Jun 2021cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Scene text image super-resolution (STISR) aims to improve the resolution and visual quality of low-resolution (LR) scene text images, and consequently boost the performance of text recognition. However, most of existing STISR methods regard text images as natural scene images, ignoring the categorical information of text. In this paper, we make an inspiring attempt to embed categorical text prior into STISR model training. Specifically, we adopt the character probability sequence as the text prior, which can be obtained conveniently from a text recognition model. The text prior provides categorical guidance to recover high-resolution (HR) text images. On the other hand, the reconstructed HR image can refine the text prior in return. Finally, we present a multi-stage text prior guided super-resolution (TPGSR) framework for STISR. Our experiments on the benchmark TextZoom dataset show that TPGSR can not only effectively improve the visual quality of scene text images, but also significantly improve the text recognition accuracy over existing STISR methods. Our model trained on TextZoom also demonstrates certain generalization capability to the LR images in other datasets.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 29 Jun 2021.

Builds on

33 of 56 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  5. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  6. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  10. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  11. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  12. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
21 more
  1. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  2. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  3. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  4. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  5. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 371
  6. 2019Scene Text Visual Question Answeringcited by 331
  7. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 286
  8. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  9. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  10. 2014Reading Text in the Wild with Convolutional Neural Networkscited by 122
  11. 2020SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognitioncited by 119
  12. 2019Zoom To Learn, Learn To Zoomcited by 115
  13. 2017Focusing Attention: Towards Accurate Text Recognition in Natural Imagescited by 110
  14. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  15. 2020Scene Text Image Super-Resolution in the Wildcited by 63
  16. 2015Reading Scene Text in Deep Convolutional Sequencescited by 44
  17. 2019Towards Real Scene Super-Resolution with Raw Imagescited by 44
  18. 2019Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Netcited by 35
  19. 2019TextSR: Content-Aware Text Super-Resolution Guided by Recognitioncited by 26
  20. 2015Boosting Optical Character Recognition: A Super-Resolution Approachcited by 19
  21. 2018Deep Laplacian Pyramid Network for Text Images Super-Resolutioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 14; 2024: 4; 2025: 10; 2026: 4.

37 papers.

Sort:

By area:

  1. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  2. 2021Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Studycited by 53
  3. 2024TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understandingcited by 38
  4. 2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
  5. 2021Text Gestalt: Stroke-Aware Scene Text Image Super-Resolutioncited by 28
  6. 2022C3-STISR: Scene Text Image Super-resolution with Triple Cluescited by 26
  7. 2023Diffusion-based Blind Text Image Super-Resolutioncited by 25
  8. 2023Learning Generative Structure Prior for Blind Text Image Super-resolutioncited by 24
  9. 2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
  10. 2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 19
  11. 2023A Benchmark for Chinese-English Scene Text Image Super-resolutioncited by 17
  12. 2023Improving Scene Text Image Super-resolution via Dual Prior Modulation Networkcited by 15
25 more
  1. 2023Scene Text Image Super-resolution based on Text-conditional Diffusion Modelscited by 15
  2. 2023TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolutioncited by 10
  3. 2022Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blockscited by 8
  4. 2023Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancementcited by 8
  5. 2024Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processingcited by 8
  6. 2023Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolutioncited by 5
  7. 2023Deep Image Compression Using Scene Text Quality Assessmentcited by 4
  8. 2023PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolutioncited by 4
  9. 2025Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarioscited by 4
  10. 2023One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfercited by 3
  11. 2025Enhanced Generative Structure Prior for Chinese Text Image Super-resolutioncited by 3
  12. 2025SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioningcited by 3
  13. 2025Unified Diffusion Transformer for High-fidelity Text-Aware Image Restorationcited by 3
  14. 2025MF-LPR2: Multi-Frame License Plate Image Restoration and Recognition using Optical Flowcited by 2
  15. 2024Efficient scene text image super-resolution with semantic guidancecited by 1
  16. 2024Task-driven single-image super-resolution reconstruction of document scanscited by 1
  17. 2025NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Priorcited by 1
  18. 2026DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolutioncited by 1
  19. 2026PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolutioncited by 1
  20. 2023ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenescited by 0
  21. 2023HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolutioncited by 0
  22. 2025Local-Global Context-Aware and Structure-Preserving Image Super-Resolutioncited by 0
  23. 2025CharDiff-LP: A Diffusion Model with Character-Level Guidance for License Plate Image Restorationcited by 0
  24. 2026DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulationcited by 0
  25. 2026TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolutioncited by 0