BookNet: Book Image Rectification via Cross-Page Attention Network

TL;DR

BookNet is a novel deep learning framework that effectively rectifies complex curved book images by modeling the geometric relationship between adjacent pages using cross-page attention, supported by new synthetic and real datasets.

Contribution

It introduces the first end-to-end dual-page rectification network with cross-page attention and provides large-scale synthetic and real datasets for training and evaluation.

Findings

Outperforms existing methods on rectification accuracy

Effectively models inter-page geometric relationships

Demonstrates robustness on real-world book images

Abstract

Book image rectification presents unique challenges in document image processing due to complex geometric distortions from binding constraints, where left and right pages exhibit distinctly asymmetric curvature patterns. However, existing single-page document image rectification methods fail to capture the coupled geometric relationships between adjacent pages in books. In this work, we introduce BookNet, the first end-to-end deep learning framework specifically designed for dual-page book image rectification. BookNet adopts a dual-branch architecture with cross-page attention mechanisms, enabling it to estimate warping flows for both individual pages and the complete book spread, explicitly modeling how left and right pages influence each other. Moreover, to address the absence of specialized datasets, we present Book3D, a large-scale synthetic dataset for training, and Book100, a comprehensive real-world benchmark for evaluation. Extensive experiments demonstrate that BookNet outperforms existing state-of-the-art methods on book image rectification. Code and dataset will be made publicly available.