# Light-weight Document Image Cleanup using Perceptual Loss

arXiv: https://arxiv.org/abs/2105.09076 · HTML: https://mlsanity.com/paper/2105.09076/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 54 references that are in the map.
- First posted on arXiv 19 May 2021.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement](https://mlsanity.com/paper/2010.08764/) (2020)
- [Document Rectification and Illumination Correction using a Patch-based CNN](https://mlsanity.com/paper/1909.09470/) (2019)
- [SROBB: Targeted Perceptual Loss for Single Image Super-Resolution](https://mlsanity.com/paper/1908.07222/) (2019)
- [Document Image Binarization with Fully Convolutional Neural Networks](https://mlsanity.com/paper/1708.03276/) (2017)
- [Convolutional CRFs for Semantic Segmentation](https://mlsanity.com/paper/1805.04777/) (2018)
- [Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal](https://mlsanity.com/paper/1904.09763/) (2019)
- [Robust Regression For Image Binarization Under Heavy Noises and Nonuniform Background](https://mlsanity.com/paper/1609.08078/) (2016)

## Built on by (most cited first, 6 of 6)

- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [A Survey on Deep learning based Document Image Enhancement](https://mlsanity.com/paper/2112.02719/) (2021)
- [Binarizing Documents by Leveraging both Space and Frequency](https://mlsanity.com/paper/2404.17243/) (2024)
- [Confidence Score for Unsupervised Foreground Background Separation of Document Images](https://mlsanity.com/paper/2204.04044/) (2022)
- [DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removal](https://mlsanity.com/paper/2507.01422/) (2025)

## Abstract (arXiv)

Smartphones have enabled effortless capturing and sharing of documents in digital form. The documents, however, often undergo various types of degradation due to aging, stains, or shortcoming of capturing environment such as shadow, non-uniform lighting, etc., which reduces the comprehensibility of the document images. In this work, we consider the problem of document image cleanup on embedded applications such as smartphone apps, which usually have memory, energy, and latency limitations due to the device and/or for best human user experience. We propose a light-weight encoder decoder based convolutional neural network architecture for removing the noisy elements from document images. To compensate for generalization performance with a low network capacity, we incorporate the perceptual loss for knowledge transfer from pre-trained deep CNN network in our loss function. In terms of the number of parameters and product-sum operations, our models are 65-1030 and 3-27 times, respectively, smaller than existing state-of-the-art document enhancement models. Overall, the proposed models offer a favorable resource versus accuracy trade-off and we empirically illustrate the efficacy of our approach on several real-world benchmark datasets.