mlsanityData to 7 Oct 2026

End-to-End Unsupervised Document Image Blind Denoising

arXiv 2105.09437 ↗First posted 19 May 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Removing noise from scanned pages is a vital step before their submission to the optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However, this assumption is rarely met in real settings. Besides, there is no single model that can remove various noise types from documents. Here, we propose a unified end-to-end unsupervised deep learning model, for the first time, that can effectively remove multiple types of noise, including salt & pepper noise, blurred and/or faded text, as well as watermarks from documents at various levels of intensity. We demonstrate that the proposed model significantly improves the quality of scanned images and the OCR of the pages on several test datasets.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 19 May 2021.

Builds on

22 of 40 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  4. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  5. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  6. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  7. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  8. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  9. 2015Evaluation of Deep Convolutional Nets for Document Image Classification and Retrievalcited by 212
  10. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  11. 2018Residual Dense Network for Image Restorationcited by 181
  12. 2019Real Image Denoising with Feature Attentioncited by 176
10 more
  1. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  2. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  3. 2019Deep Learning on Image Denoising: An overviewcited by 128
  4. 2020Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalizationcited by 92
  5. 2020Unpaired Learning of Deep Image Denoisingcited by 74
  6. 2019Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restorationcited by 73
  7. 2020DE-GAN: A Conditional Generative Adversarial Network for Document Enhancementcited by 44
  8. 2019GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Imagescited by 12
  9. 2019Learning to Clean: A GAN Perspectivecited by 7
  10. 2018Deep Reader: Information extraction from Document images via relation extraction and Natural Languagecited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 2.

7 papers.

  1. 2022Augraphy: A Data Augmentation Library for Document Imagescited by 14
  2. 2024High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformercited by 12
  3. 2024Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processingcited by 8
  4. 2021A Survey on Deep learning based Document Image Enhancementcited by 7
  5. 2023DECDM: Document Enhancement using Cycle-Consistent Diffusion Modelscited by 1
  6. 2022EraseNet: A Recurrent Residual Network for Supervised Document Cleaningcited by 0
  7. 2023ShabbyPages: A Reproducible Document Denoising and Binarization Datasetcited by 0