Geometric Representation Learning for Document Image Rectification

TL;DR

This paper introduces DocGeoNet, a novel geometric representation learning framework that leverages 3D shape and textline attributes to improve document image rectification, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a new geometric representation learning approach incorporating 3D shape and textlines for enhanced document rectification.

Findings

Outperforms state-of-the-art methods on DocUNet Benchmark.

Effectively utilizes geometric constraints for better rectification.

Demonstrates robustness on a new DIR300 dataset.

Abstract

In document image rectification, there exist rich geometric constraints between the distorted image and the ground truth one. However, such geometric constraints are largely ignored in existing advanced solutions, which limits the rectification performance. To this end, we present DocGeoNet for document image rectification by introducing explicit geometric representation. Technically, two typical attributes of the document image are involved in the proposed geometric representation learning, i.e., 3D shape and textlines. Our motivation arises from the insight that 3D shape provides global unwarping cues for rectifying a distorted document image while overlooking the local structure. On the other hand, textlines complementarily provide explicit geometric constraints for local patterns. The learned geometric representation effectively bridges the distorted image and the ground truth one. Extensive experiments show the effectiveness of our framework and demonstrate the superiority of our DocGeoNet over state-of-the-art methods on both the DocUNet Benchmark dataset and our proposed DIR300 test set. The code is available at https://github.com/fh2019ustc/DocGeoNet.