mlsanityData to 14 Oct 2026

PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution

arXiv 2311.17955 ↗First posted 29 Nov 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text images, visual structure and semantic information, affect the recognition performance significantly. To mitigate the effects from these factors, this paper proposes a Prior-Enhanced Attention Network (PEAN). Specifically, an attention-based modulation module is leveraged to understand scene text images by neatly perceiving the local and global dependence of images, despite the shape of the text. Meanwhile, a diffusion-based module is developed to enhance the text prior, hence offering better guidance for the SR network to generate SR images with higher semantic accuracy. Additionally, a multi-task learning paradigm is employed to optimize the network, enabling the model to generate legible SR images. As a result, PEAN establishes new SOTA results on the TextZoom benchmark. Experiments are also conducted to analyze the importance of the enhanced text prior as a means of improving the performance of the SR network. Code is available at https://github.com/jdfxzzy/PEAN.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 56 of its 83 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

56 of 83 references.

References · 56

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  9. 2020Denoising Diffusion Implicit Modelscited by 9,781
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  12. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
38 more
  1. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  3. 2015Spatial Transformer Networkscited by 1,429
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  6. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  7. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  8. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  9. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  10. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  11. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  12. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  13. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  14. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  15. 2022How Do Vision Transformers Work?cited by 307
  16. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizercited by 262
  17. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 255
  18. 2021Deblurring via Stochastic Refinementcited by 249
  19. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  20. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  21. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
  22. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 149
  23. 2022Stripformer: Strip Transformer for Fast Image Deblurringcited by 140
  24. 2020Towards Accurate Scene Text Recognition with Semantic Reasoning Networkscited by 131
  25. 2019Zoom To Learn, Learn To Zoomcited by 115
  26. 2021From Two to One: A New Scene Text Recognizer with Visual Language Modeling Networkcited by 97
  27. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 77
  28. 2020Scene Text Image Super-Resolution in the Wildcited by 63
  29. 2017Pixel Recursive Super Resolutioncited by 44
  30. 2021PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognitioncited by 41
  31. 2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
  32. 2023DocDiff: Document Enhancement via Residual Diffusion Modelscited by 37
  33. 2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
  34. 2019A Multi-Object Rectified Attention Network for Scene Text Recognitioncited by 30
  35. 2021Text Gestalt: Stroke-Aware Scene Text Image Super-Resolutioncited by 28
  36. 2022C3-STISR: Scene Text Image Super-resolution with Triple Cluescited by 26
  37. 2020RoadText-1K: Text Detection & Recognition Dataset for Driving Videoscited by 25
  38. 2023Towards Authentic Face Restoration with Iterative Diffusion Models and Beyondcited by 18

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

4 papers.

  1. 2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 19
  2. 2025Enhanced Generative Structure Prior for Chinese Text Image Super-resolutioncited by 3
  3. 2026DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolutioncited by 1
  4. 2026PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolutioncited by 1