mlsanityData to 7 Oct 2026

DocEnTr: An End-to-End Document Image Enhancement Transformer

arXiv 2201.10252 ↗First posted 25 Jan 2022cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: urlhttps://github.com/dali92002/DocEnTR.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 25 Jan 2022.

Builds on

20 of 44 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2016Layer Normalizationcited by 5,579
  7. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  8. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 406
  9. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  10. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  11. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
  12. 2021LaTr: Layout-Aware Transformer for Scene-Text VQAcited by 72
8 more
  1. 2020DE-GAN: A Conditional Generative Adversarial Network for Document Enhancementcited by 44
  2. 2021DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correctioncited by 38
  3. 2017Document Image Binarization with Fully Convolutional Neural Networkscited by 25
  4. 2017A selectional auto-encoder approach for document image binarizationcited by 22
  5. 2021Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documentscited by 17
  6. 2018Improving Document Binarization via Adversarial Noise-Texture Augmentationcited by 9
  7. 2021Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancementcited by 7
  8. 2019Patch redundancy in images: a statistical testing framework and some applicationscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 8; 2024: 5; 2025: 3; 2026: 6.

28 papers.

Sort:

By area:

  1. 2023DocDiff: Document Enhancement via Residual Diffusion Modelscited by 37
  2. 2022OCR-IDL: OCR Annotations for Industry Document Library Datasetcited by 35
  3. 2022Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancementcited by 16
  4. 2024High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformercited by 12
  5. 2024NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancementcited by 9
  6. 2022Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networkscited by 5
  7. 2023DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarizationcited by 4
  8. 2023ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documentscited by 3
  9. 2023DocStormer: Revitalizing Multi-Degraded Colored Document Images to Pristine PDFcited by 3
  10. 2024Binarizing Documents by Leveraging both Space and Frequencycited by 3
  11. 2023A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancementcited by 2
  12. 2024Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancementcited by 2
16 more
  1. 2025TextDoctor: Unified Document Image Inpainting via Patch Pyramid Diffusion Modelscited by 2
  2. 2025MFE-GAN: Efficient GAN-based Framework for Document Image Enhancement and Binarization with Multi-scale Feature Extractioncited by 2
  3. 2022Digitizing Historical Balance Sheet Data: A Practitioner's Guidecited by 1
  4. 2022Mutual Guidance and Residual Integration for Image Enhancementcited by 1
  5. 2023arXiVeri: Automatic table verification with GPTcited by 1
  6. 2023Semantic Segmentation Using Super Resolution Technique as Pre-Processingcited by 1
  7. 2023DECDM: Document Enhancement using Cycle-Consistent Diffusion Modelscited by 1
  8. 2024LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approachcited by 1
  9. 2026Unveiling Text in Challenging Stone Inscriptions: A Character-Context-Aware Patching Strategy for Binarizationcited by 1
  10. 2026DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarizationcited by 1
  11. 2022Variational Augmentation for Enhancing Historical Document Image Binarizationcited by 0
  12. 2025MatteViT: High-Frequency-Aware Document Shadow Removal with Shadow Matte Guidancecited by 0
  13. 2026DocRevive: A Unified Pipeline for Document Text Restorationcited by 0
  14. 2026DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppressioncited by 0
  15. 2026SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operationcited by 0
  16. 2026ENet-GP: Unified Document Image Restorationcited by 0