mlsanityData to 14 Oct 2026

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy

arXiv 2505.20429 ↗First posted 26 May 2025cs.CL cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency, thereby improving text extraction from degraded historical documents. First, we synthesize document-image pairs from plaintext, rendering them with diverse fonts and layouts and then applying a randomly ordered set of degradation operations. An image restoration model is trained on this synthetic data, using multi-directional patch extraction and fusion to process large images. Second, a ByT5 post-OCR model, fine-tuned on synthetic historical text pairs, addresses remaining OCR errors. Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that the PreP-OCR pipeline reduces character error rates by 63.9-70.3% compared to OCR on raw images. Our pipeline demonstrates the potential of integrating image restoration with linguistic error correction for digitizing historical archives.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 37 of its 74 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

37 of 74 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  6. 2017Improved Training of Wasserstein GANscited by 2,235
  7. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  8. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  10. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  11. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  12. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
25 more
  1. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  2. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  3. 2020Pre-Trained Image Processing Transformercited by 893
  4. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 509
  5. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  6. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  7. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 362
  8. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 255
  9. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 180
  10. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 147
  11. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  12. 2022DataPerf: Benchmarks for Data-Centric AI Developmentcited by 90
  13. 2024CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacycited by 81
  14. 2025PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selectioncited by 61
  15. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  16. 2022Realistic Blur Synthesis for Learning Image Deblurringcited by 53
  17. 2024LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steeringcited by 51
  18. 2025CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Processcited by 51
  19. 2025Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoningcited by 32
  20. 2020OCR Post Correction for Endangered Language Textscited by 31
  21. 2022A Benchmark and Dataset for Post-OCR text correction in Sanskritcited by 10
  22. 2024Predicting the Original Appearance of Damaged Historical Documentscited by 9
  23. 2024Advancing Post-OCR Correction: A Comparative Study of Synthetic Datacited by 8
  24. 2018Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskritcited by 7
  25. 2015OCR accuracy improvement on document images through a novel pre-processing approachcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLMcited by 37
  2. 2026OptiSQL: Executable SQL Generation from Optical Tokenscited by 0
  3. 2026MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Texturescited by 0
  4. 2026How Far Can Synthetic Data Take Thai OCR?cited by 0
  5. 2026DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognitioncited by 0