Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild

TL;DR

Marior is a novel document dewarping pipeline that iteratively removes margins and rectifies content in a coarse-to-fine manner, effectively handling diverse real-world document images for improved OCR and visual quality.

Contribution

This work introduces Marior, a complete pipeline with margin removal and iterative content rectification modules, addressing practical challenges in dewarping documents in the wild.

Findings

Achieves state-of-the-art results on public benchmarks.

Effectively handles documents with large margins or no margins.

Adaptive iteration improves dewarping quality progressively.

Abstract

Camera-captured document images usually suffer from perspective and geometric deformations. It is of great value to rectify them when considering poor visual aesthetics and the deteriorated performance of OCR systems. Recent learning-based methods intensively focus on the accurately cropped document image. However, this might not be sufficient for overcoming practical challenges, including document images either with large marginal regions or without margins. Due to this impracticality, users struggle to crop documents precisely when they encounter large marginal regions. Simultaneously, dewarping images without margins is still an insurmountable problem. To the best of our knowledge, there is still no complete and effective pipeline for rectifying document images in the wild. To address this issue, we propose a novel approach called Marior (Margin Removal and \Iterative Content Rectification). Marior follows a progressive strategy to iteratively improve the dewarping quality and readability in a coarse-to-fine manner. Specifically, we divide the pipeline into two modules: margin removal module (MRM) and iterative content rectification module (ICRM). First, we predict the segmentation mask of the input image to remove the margin, thereby obtaining a preliminary result. Then we refine the image further by producing dense displacement flows to achieve content-aware rectification. We determine the number of refinement iterations adaptively. Experiments demonstrate the state-of-the-art performance of our method on public benchmarks. The resources are available at https://github.com/ZZZHANG-jx/Marior for further comparison.