# Rethinking Supervision in Document Unwarping: A Self-consistent Flow-free Approach

arXiv: https://arxiv.org/abs/2610.15445 · HTML: https://mlsanity.com/paper/2610.15445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 78 references that are in the map.
- First posted on arXiv 11 Oct 2026.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Deep Snake for Real-Time Instance Segmentation](https://mlsanity.com/paper/2001.01629/) (2020)
- [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)
- [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)
- [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)
- [Multimodal Pre-training Based on Graph Attention Network for Document Understanding](https://mlsanity.com/paper/2203.13530/) (2022)
- [Fourier Document Restoration for Robust Document Dewarping and Recognition](https://mlsanity.com/paper/2203.09910/) (2022)
- [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)
- [Can You Read Me Now? Content Aware Rectification using Angle Supervision](https://mlsanity.com/paper/2008.02231/) (2020)
- [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)
- [Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach](https://mlsanity.com/paper/2207.14801/) (2022)
- [Intrinsic Decomposition of Document Images In-the-Wild](https://mlsanity.com/paper/2011.14447/) (2020)
- [Geometric Rectification of Creased Document Images based on Isometric Mapping](https://mlsanity.com/paper/2212.08365/) (2022)

## Abstract (arXiv)

In recent years, the proliferation of smartphones has led to an upsurge in the digitization of document files via these portable devices. However, images captured by smartphones often suffer from distortions, thereby negatively affecting digital preservation and downstream applications. To address this issue, we introduce DRNet, a novel deep network for document image rectification. Our approach is based on three key designs. Firstly, we exploit the intrinsic geometric consistency inherent in document images to guide the learning process of distortion rectification. Secondly, we design a coarse-to-fine rectification network to leverage the representations derived from the distorted document image, thereby enhancing the rectification result. Thirdly, we propose a unique perspective for supervising the learning of rectification networks, where undistorted document images are employed for supervision, which is free of warping mesh as ground truth in existing methods. Technically, both low-level pixel alignment and high-level semantic alignment jointly contribute to the learning of the mapping relationship between deformed document images and distortion-free ones. We evaluate our method on the challenging DocUNet Benchmark dataset, where it sets a series of state-of-the-art records, demonstrating the superiority of our approach compared to existing learning-based solutions. Additionally, we conduct a comprehensive series of ablation experiments to further validate the effectiveness and merits of our method.