# DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction

arXiv: https://arxiv.org/abs/2110.12942 · HTML: https://mlsanity.com/paper/2110.12942/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [DeVLBert: Learning Deconfounded Visio-Linguistic Representations](https://mlsanity.com/paper/2008.06884/) (2020)
- [Document Rectification and Illumination Correction using a Patch-based CNN](https://mlsanity.com/paper/1909.09470/) (2019)
- [Multiview Rectification of Folded Documents](https://mlsanity.com/paper/1606.00166/) (2016)
- [Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network](https://mlsanity.com/paper/2104.06815/) (2021)
- [Can You Read Me Now? Content Aware Rectification using Angle Supervision](https://mlsanity.com/paper/2008.02231/) (2020)
- [Semi-supervised Multi-modal Emotion Recognition with Cross-Modal Distribution Matching](https://mlsanity.com/paper/2009.02598/) (2020)

## Built on by (most cited first, 30 of 39)

- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Geometric Representation Learning for Document Image Rectification](https://mlsanity.com/paper/2210.08161/) (2022)
- [DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks](https://mlsanity.com/paper/2405.04408/) (2024)
- [DocScanner: Robust Document Image Rectification with Progressive Learning](https://mlsanity.com/paper/2110.14968/) (2021)
- [Revisiting Document Image Dewarping by Grid Regularization](https://mlsanity.com/paper/2203.16850/) (2022)
- [Fourier Document Restoration for Robust Document Dewarping and Recognition](https://mlsanity.com/paper/2203.09910/) (2022)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild](https://mlsanity.com/paper/2207.11515/) (2022)
- [UVDoc: Neural Grid-based Document Unwarping](https://mlsanity.com/paper/2302.02887/) (2023)
- [Deep Unrestricted Document Image Rectification](https://mlsanity.com/paper/2304.08796/) (2023)
- [UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior](https://mlsanity.com/paper/2210.08216/) (2022)
- [High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer](https://mlsanity.com/paper/2410.22922/) (2024)
- [OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities](https://mlsanity.com/paper/2507.15085/) (2025)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [Geometric Rectification of Creased Document Images based on Isometric Mapping](https://mlsanity.com/paper/2212.08365/) (2022)
- [Literature Review: Computer Vision Applications in Transportation Logistics and Warehousing](https://mlsanity.com/paper/2304.06009/) (2023)
- [DocMAE: Document Image Rectification via Self-supervised Representation Learning](https://mlsanity.com/paper/2304.10341/) (2023)
- [Limb-Aware Virtual Try-On Network with Progressive Clothing Warping](https://mlsanity.com/paper/2503.14074/) (2025)
- [Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion](https://mlsanity.com/paper/2508.04055/) (2025)
- [MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary](https://mlsanity.com/paper/2307.12571/) (2023)
- [DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model](https://mlsanity.com/paper/2505.21975/) (2025)
- [DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures](https://mlsanity.com/paper/2306.05749/) (2023)
- [Progressive Limb-Aware Virtual Try-On](https://mlsanity.com/paper/2503.12588/) (2025)
- [Digitizing Historical Balance Sheet Data: A Practitioner's Guide](https://mlsanity.com/paper/2204.00052/) (2022)
- [Efficient Document Image Dewarping via Hybrid Deep Learning and Cubic Polynomial Geometry Restoration](https://mlsanity.com/paper/2501.03145/) (2025)
- [ForCenNet: Foreground-Centric Network for Document Image Rectification](https://mlsanity.com/paper/2507.19804/) (2025)
- [bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents](https://mlsanity.com/paper/2308.10647/) (2023)
- [Unfolder: Fast localization and image rectification of a document with a crease from folding in half](https://mlsanity.com/paper/2312.00467/) (2023)
- [Document Image Rectification Bases on Self-Adaptive Multitask Fusion](https://mlsanity.com/paper/2505.06038/) (2025)
- [GL-PGENet: A Parameterized Generation Framework for Robust Document Image Enhancement](https://mlsanity.com/paper/2505.22021/) (2025)

## Abstract (arXiv)

In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifically, DocTr consists of a geometric unwarping transformer and an illumination correction transformer. By setting a set of learned query embedding, the geometric unwarping transformer captures the global context of the document image by self-attention mechanism and decodes the pixel-wise displacement solution to correct the geometric distortion. After geometric unwarping, our illumination correction transformer further removes the shading artifacts to improve the visual quality and OCR accuracy. Extensive evaluations are conducted on several datasets, and superior results are reported against the state-of-the-art methods. Remarkably, our DocTr achieves 20.02% Character Error Rate (CER), a 15% absolute improvement over the state-of-the-art methods. Moreover, it also shows high efficiency on running time and parameter count. The results will be available at https://github.com/fh2019ustc/DocTr for further comparison.