Document Image Rectification Bases on Self-Adaptive Multitask Fusion
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 39 references indexed in Scilit:
- DocScanner: Robust Document Image Rectification with Progressive LearningInternational Journal of Computer Vision, 2025
- DocPedia: unleashing the power of large multimodal model in the frequency domain for versatile document understandingScience China Information Sciences, 2024
- InstructIR: High-Quality Image Restoration Following Human Instructions2024
- Multi-task disagreement-reducing multimodal sentiment fusion networkImage and Vision Computing, 2024
- IIMT-net: Poly-1 weights balanced multi-task network for semantic segmentation and depth estimation using interactive informationImage and Vision Computing, 2024
- Am I readable? Transfer learning based document image rectificationInternational Journal on Document Analysis and Recognition (IJDAR), 2024
- AutoSegEdge: Searching for the edge device real-time semantic segmentation based on multi-task learningImage and Vision Computing, 2023
- Dewarping Document Image by Displacement Flow Estimation with Fully Convolutional Network2020
- Shape from shading for the digitization of curved documentsMachine Vision and Applications, 2007
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005