# D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping

arXiv: https://arxiv.org/abs/2507.08492 · HTML: https://mlsanity.com/paper/2507.08492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Builds on (most cited first, 26 of 26)

- [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)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding](https://mlsanity.com/paper/2311.11810/) (2023)
- [M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis](https://mlsanity.com/paper/2305.08719/) (2023)
- [DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction](https://mlsanity.com/paper/2110.12942/) (2021)
- [DocDiff: Document Enhancement via Residual Diffusion Models](https://mlsanity.com/paper/2305.03892/) (2023)
- [DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming](https://mlsanity.com/paper/2406.19101/) (2024)
- [Multiview Rectification of Folded Documents](https://mlsanity.com/paper/1606.00166/) (2016)
- [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)
- [Cross-Domain Document Object Detection: Benchmark Suite and Method](https://mlsanity.com/paper/2003.13197/) (2020)
- [Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network](https://mlsanity.com/paper/2104.06815/) (2021)
- [Document Dewarping with Control Points](https://mlsanity.com/paper/2203.10543/) (2022)
- [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)
- [Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach](https://mlsanity.com/paper/2207.14801/) (2022)
- [RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering](https://mlsanity.com/paper/2010.12917/) (2020)
- [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)

## Abstract (arXiv)

Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a fine-grained deformation perception model that focuses on Dual Dimensions of document horizontal-vertical-lines to improve document Dewarping called D2Dewarp. It can perceive distortion trends in different directions across document details. To combine the horizontal and vertical granularity features, an effective fusion module based on X and Y coordinate is designed to facilitate interaction and constraint between the two dimensions for feature complementarity. Due to the lack of annotated line features in current public dewarping datasets, we also propose an automatic fine-grained annotation method using public document texture images and automatic rendering engine to build a new large-scale distortion training dataset named DocDewarpHV. On three public Chinese and English benchmarks, both quantitative and qualitative results show that our method achieves better rectification results compared with the state-of-the-art methods. The code and dataset are available at https://github.com/xiaomore/D2Dewarp.