arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.07925cs.CV
收藏

Polar-Doc:极坐标表示下带多范围约束的单阶段文档去扭曲

Polar-Doc: One-Stage Document Dewarping with Multi-Scope Constraints under Polar Representation

Duke Kunshan University(昆山杜克大学)

Weiguang Zhang, Qiufeng Wang, Kaizhu Huang

AI总结:

针对现有文档去扭曲方法笛卡尔坐标表示效率低、多采用两阶段流程的问题,提出极坐标表示的单阶段Polar-Doc方法及多范围Polar-Doc-IOU损失,以更少参数量在像素对齐和OCR指标上实现新的SOTA性能。

摘要:

文档去扭曲旨在消除拍摄文档中的几何形变以助力文本识别,近年来已取得长足进展,但问题仍远未解决。当前最优方法通常利用笛卡尔坐标学习一组形变控制点,然而这种表示方式不利于去扭曲模型高效学习形变信息。本研究探索将极坐标表示应用于文档去扭曲中的每个点,即Polar-Doc方法。与目前大多数通常采用两阶段流程的研究不同,极坐标表示为分割网络和去扭曲网络提供了统一的点回归框架,可在单阶段内完成。这种统一模式使整个模型在端到端优化流程下的学习效率更高,同时实现了紧凑的表示形式。此外,我们提出了一种新颖的多范围Polar-Doc-IOU损失,在极坐标表示下以基于网格的正则化方式约束控制点之间的关系。在两个基准数据集上的视觉对比和定量实验表明,我们的带多范围约束的单阶段模型参数量远少于其他主流同类模型,同时在像素对齐指标和OCR指标上均取得了新的最优性能。源代码将发布于\url{*****}。

英文摘要:

Document dewarping, aiming to eliminate geometric deformation in photographed documents to benefit text recognition, has made great progress in recent years but is still far from being solved. While Cartesian coordinates are typically leveraged by state-of-the-art approaches to learn a group of deformation control points, such representation is not efficient for dewarping model to learn the deformation information. In this work, we explore Polar coordinates representation for each point in document dewarping, namely Polar-Doc. In contrast to most current works adopting a two-stage pipeline typically, Polar representation enables a unified point regression framework for both segmentation and dewarping network in one single stage. Such unification makes the whole model more efficient to learn under an end-to-end optimization pipeline, and also obtains a compact representation. Furthermore, we propose a novel multi-scope Polar-Doc-IOU loss to constrain the relationship among control points as a grid-based regularization under the Polar representation. Visual comparisons and quantitative experiments on two benchmarks show that, with much fewer parameters than the other mainstream counterparts, our one-stage model with multi-scope constraints achieves new state-of-the-art performance on both pixel alignment metrics and OCR metrics. Source codes will be available at \url{*****}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑