Multiview Rectification of Folded Documents

TL;DR

This paper introduces a robust method for automatically rectifying curved or folded paper sheets from multiple images, enabling more accurate digital document unwrapping without expensive equipment.

Contribution

It presents a novel developable surface-based rectification technique using ridge-aware 3D reconstruction and $ ext{L}_1$ conformal mapping, improving over prior methods that require costly scanners or oversimplified models.

Findings

Effective unwrapping of various folded documents

Works with regular images, no specialized hardware needed

Demonstrates superior accuracy on diverse examples

Abstract

Digitally unwrapping images of paper sheets is crucial for accurate document scanning and text recognition. This paper presents a method for automatically rectifying curved or folded paper sheets from a few images captured from multiple viewpoints. Prior methods either need expensive 3D scanners or model deformable surfaces using over-simplified parametric representations. In contrast, our method uses regular images and is based on general developable surface models that can represent a wide variety of paper deformations. Our main contribution is a new robust rectification method based on ridge-aware 3D reconstruction of a paper sheet and unwrapping the reconstructed surface using properties of developable surfaces via $\ell_1$ conformal mapping. We present results on several examples including book pages, folded letters and shopping receipts.