# UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

arXiv: https://arxiv.org/abs/2210.08216 · HTML: https://mlsanity.com/paper/2210.08216/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 15 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [NIPS 2016 Tutorial: Generative Adversarial Networks](https://mlsanity.com/paper/1701.00160/) (2016)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Generalization and Equilibrium in Generative Adversarial Nets (GANs)](https://mlsanity.com/paper/1703.00573/) (2017)
- [Dual Learning for Machine Translation](https://mlsanity.com/paper/1611.00179/) (2016)
- [A Survey on Generative Adversarial Networks: Variants, Applications, and Training](https://mlsanity.com/paper/2006.05132/) (2020)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [Learning Dense Correspondence via 3D-guided Cycle Consistency](https://mlsanity.com/paper/1604.05383/) (2016)
- [Disentangling factors of variation in deep representations using adversarial training](https://mlsanity.com/paper/1611.03383/) (2016)
- [Perceptual Generative Adversarial Networks for Small Object Detection](https://mlsanity.com/paper/1706.05274/) (2017)
- [SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation](https://mlsanity.com/paper/1706.01805/) (2017)
- [DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction](https://mlsanity.com/paper/2110.12942/) (2021)
- [Document Rectification and Illumination Correction using a Patch-based CNN](https://mlsanity.com/paper/1909.09470/) (2019)
- [Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal](https://mlsanity.com/paper/1904.09763/) (2019)
- [It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality](https://mlsanity.com/paper/1912.01707/) (2019)
- [SRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial Networks](https://mlsanity.com/paper/1903.11821/) (2019)

## Built on by (most cited first, 15 of 15)

- [DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks](https://mlsanity.com/paper/2405.04408/) (2024)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer](https://mlsanity.com/paper/2410.22922/) (2024)
- [Predicting the Original Appearance of Damaged Historical Documents](https://mlsanity.com/paper/2412.11634/) (2024)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [Literature Review: Computer Vision Applications in Transportation Logistics and Warehousing](https://mlsanity.com/paper/2304.06009/) (2023)
- [Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion](https://mlsanity.com/paper/2508.04055/) (2025)
- [Hierarchical Evidence-Driven Reasoning for Long Document Understanding](https://mlsanity.com/paper/2607.04625/) (2026)
- [Survey on Controlable Image Synthesis with Deep Learning](https://mlsanity.com/paper/2307.10275/) (2023)
- [Unfolder: Fast localization and image rectification of a document with a crease from folding in half](https://mlsanity.com/paper/2312.00467/) (2023)
- [GL-PGENet: A Parameterized Generation Framework for Robust Document Image Enhancement](https://mlsanity.com/paper/2505.22021/) (2025)
- [DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removal](https://mlsanity.com/paper/2507.01422/) (2025)
- [MatteViT: High-Frequency-Aware Document Shadow Removal with Shadow Matte Guidance](https://mlsanity.com/paper/2512.08789/) (2025)
- [SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction](https://mlsanity.com/paper/2609.15503/) (2026)
- [ENet-GP: Unified Document Image Restoration](https://mlsanity.com/paper/2609.33758/) (2026)

## Abstract (arXiv)

Document images captured by mobile devices are usually degraded by uncontrollable illumination, which hampers the clarity of document content. Recently, a series of research efforts have been devoted to correcting the uneven document illumination. However, existing methods rarely consider the use of ambient light information, and usually rely on paired samples including degraded and the corrected ground-truth images which are not always accessible. To this end, we propose UDoc-GAN, the first framework to address the problem of document illumination correction under the unpaired setting. Specifically, we first predict the ambient light features of the document. Then, according to the characteristics of different level of ambient lights, we re-formulate the cycle consistency constraint to learn the underlying relationship between normal and abnormal illumination domains. To prove the effectiveness of our approach, we conduct extensive experiments on DocProj dataset under the unpaired setting. Compared with the state-of-the-art approaches, our method demonstrates promising performance in terms of character error rate (CER) and edit distance (ED), together with better qualitative results for textual detail preservation. The source code is now publicly available at https://github.com/harrytea/UDoc-GAN.