D2Dewarp：基于双维度几何表示学习的文档图像矫正
D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping
提出基于水平-垂直双维度线特征的细粒度形变感知模型，并利用渲染引擎自动生成带线标注的大规模畸变数据集，可复用于其他需要几何结构先验的文档或场景图像矫正任务。
原文依据 we propose a fine-grained deformation perception model that focuses on Dual Dimensions of document horizontal-vertical-lines
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在深度学习时代，文档图像矫正仍然是一项具有挑战性的任务。现有方法通过利用文本行感知取得了改进，但通常只关注单一的水平维度。本文提出了一种细粒度形变感知模型，聚焦于文档水平-垂直线条的双维度以改进文档矫正，称为D2Dewarp。该模型能够感知文档细节中不同方向的畸变趋势。为了融合水平和垂直的粒度特征，设计了一个基于X和Y坐标的有效融合模块，以促进两个维度之间的交互与约束，实现特征互补。由于当前公开的矫正数据集中缺乏标注的线条特征，我们还提出了一种自动细粒度标注方法，利用公开的文档纹理图像和自动渲染引擎构建了一个名为DocDewarpHV的新大规模畸变训练数据集。代码和数据集将公开释放。在三个公开的中英文基准上，定量和定性结果均表明，与最优方法相比，我们的方法取得了更好的矫正结果。代码和数据集可在 https://github.com/xiaomore/D2Dewarp 获取。
英文原文摘要 1304 字符
Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a fine-grained deformation perception model that focuses on Dual Dimensions of document horizontal-vertical-lines to improve document Dewarping called D2Dewarp. It can perceive distortion trends in different directions across document details. To combine the horizontal and vertical granularity features, an effective fusion module based on X and Y coordinate is designed to facilitate interaction and constraint between the two dimensions for feature complementarity. Due to the lack of annotated line features in current public dewarping datasets, we also propose an automatic fine-grained annotation method using public document texture images and automatic rendering engine to build a new large-scale distortion training dataset named DocDewarpHV. The code and dataset will be publicly released. On three public Chinese and English benchmarks, both quantitative and qualitative results show that our method achieves better rectification results compared with the state-of-the-art methods. The code and dataset are available at https://github.com/xiaomore/D2Dewarp.