# Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network

arXiv: https://arxiv.org/abs/2104.06815 · HTML: https://mlsanity.com/paper/2104.06815/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 6 of 6)

- [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)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Understanding Convolution for Semantic Segmentation](https://mlsanity.com/paper/1702.08502/) (2017)
- [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)

## Built on by (most cited first, 21 of 21)

- [DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction](https://mlsanity.com/paper/2110.12942/) (2021)
- [Geometric Representation Learning for Document Image Rectification](https://mlsanity.com/paper/2210.08161/) (2022)
- [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)
- [Document Dewarping with Control Points](https://mlsanity.com/paper/2203.10543/) (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)
- [Deep Unrestricted Document Image Rectification](https://mlsanity.com/paper/2304.08796/) (2023)
- [SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning](https://mlsanity.com/paper/2308.09040/) (2023)
- [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)
- [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)
- [Efficient Document Image Dewarping via Hybrid Deep Learning and Cubic Polynomial Geometry Restoration](https://mlsanity.com/paper/2501.03145/) (2025)
- [Unfolder: Fast localization and image rectification of a document with a crease from folding in half](https://mlsanity.com/paper/2312.00467/) (2023)
- [D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping](https://mlsanity.com/paper/2507.08492/) (2025)
- [Cascaded Robust Rectification for Arbitrary Document Images](https://mlsanity.com/paper/2511.23150/) (2025)
- [ENet-GP: Unified Document Image Restoration](https://mlsanity.com/paper/2609.33758/) (2026)
- [Rethinking Supervision in Document Unwarping: A Self-consistent Flow-free Approach](https://mlsanity.com/paper/2610.15445/) (2026)

## Abstract (arXiv)

As camera-based documents are increasingly used, the rectification of distorted document images becomes a need to improve the recognition performance. In this paper, we propose a novel framework for both rectifying distorted document image and removing background finely, by estimating pixel-wise displacements using a fully convolutional network (FCN). The document image is rectified by transformation according to the displacements of pixels. The FCN is trained by regressing displacements of synthesized distorted documents, and to control the smoothness of displacements, we propose a Local Smooth Constraint (LSC) in regularization. Our approach is easy to implement and consumes moderate computing resource. Experiments proved that our approach can dewarp document images effectively under various geometric distortions, and has achieved the state-of-the-art performance in terms of local details and overall effect.