# Document Image Rectification Bases on Self-Adaptive Multitask Fusion

arXiv: https://arxiv.org/abs/2505.06038 · HTML: https://mlsanity.com/paper/2505.06038/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 62 references that are in the map.
- First posted on arXiv 9 May 2025.

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

- [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)
- [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)
- [Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2005.03572/) (2020)
- [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://mlsanity.com/paper/2202.10304/) (2022)
- [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022)
- [Geometric Multimodal Contrastive Representation Learning](https://mlsanity.com/paper/2202.03390/) (2022)
- [DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction](https://mlsanity.com/paper/2110.12942/) (2021)
- [Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions](https://mlsanity.com/paper/2112.05561/) (2021)
- [Document Rectification and Illumination Correction using a Patch-based CNN](https://mlsanity.com/paper/1909.09470/) (2019)
- [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)
- [Multimodal Pre-training Based on Graph Attention Network for Document Understanding](https://mlsanity.com/paper/2203.13530/) (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)
- [Excavation Reinforcement Learning Using Geometric Representation](https://mlsanity.com/paper/2201.11292/) (2022)
- [Table Detection for Visually Rich Document Images](https://mlsanity.com/paper/2305.19181/) (2023)
- [DocMAE: Document Image Rectification via Self-supervised Representation Learning](https://mlsanity.com/paper/2304.10341/) (2023)

## Abstract (arXiv)

Deformed document image rectification is essential for real-world document understanding tasks, such as layout analysis and text recognition. However, current multi-task methods -- such as background removal, 3D coordinate prediction, and text line segmentation -- often overlook the complementary features between tasks and their interactions. To address this gap, we propose a self-adaptive learnable multi-task fusion rectification network named SalmRec. This network incorporates an inter-task feature aggregation module that adaptively improves the perception of geometric distortions, enhances feature complementarity, and reduces negative interference. We also introduce a gating mechanism to balance features both within global tasks and between local tasks effectively. Experimental results on two English benchmarks (DIR300 and DocUNet) and one Chinese benchmark (DocReal) demonstrate that our method significantly improves rectification performance. Ablation studies further highlight the positive impact of different tasks on dewarping and the effectiveness of our proposed module.