Unifying Vision, Text, and Layout for Universal Document Processing
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Microsoft Azure Cognitive Services Research（微软Azure认知服务研究院）；Microsoft Azure Visual Document Intelligence（微软Azure视觉文档智能部门）
Zineng Tang, Ziyi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, Mohit Bansal
We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation. With a novel Vision-Text-Layout Transformer, UDOP unifies pretraining and multi-domain downstream tasks into a prompt-based sequence generation scheme. UDOP is pretrained on both large-scale unlabeled document corpora using innovative self-supervised objectives and diverse labeled data. UDOP also learns to generate document images from text and layout modalities via masked image reconstruction. To the best of our knowledge, this is the first time in the field of document AI that one model simultaneously achieves high-quality neural document editing and content customization. Our method sets the state-of-the-art on 8 Document AI tasks, e.g., document understanding and QA, across diverse data domains like finance reports, academic papers, and websites. UDOP ranks first on the leaderboard of the Document Understanding Benchmark.
The University of Sydney（悉尼大学）；The University of Western Australia（西澳大学）
Recognizing the layout of unstructured digital documents is crucial when parsing the documents into the structured, machine-readable format for downstream applications. Recent studies in Document Layout Analysis usually rely on computer vision models to understand documents while ignoring other information, such as context information or relation of document components, which are vital to capture. Our Doc-GCN presents an effective way to harmonize and integrate heterogeneous aspects for Document Layout Analysis. We first construct graphs to explicitly describe four main aspects, including synt…
Page layout analysis is a fundamental step in document processing which enables to segment a page into regions of interest. With highly complex layouts and mixed scripts, scholarly commentaries are text-heavy documents which remain challenging for state-of-the-art models. Their layout considerably varies across editions and their most important regions are mainly defined by semantic rather than graphical characteristics such as position or appearance. This setting calls for a comparison between textual, visual and hybrid approaches. We therefore assess the performances of two transformers (Lay…
Accurate document layout analysis is a key requirement for high-quality PDF document conversion. With the recent availability of public, large ground-truth datasets such as PubLayNet and DocBank, deep-learning models have proven to be very effective at layout detection and segmentation. While these datasets are of adequate size to train such models, they severely lack in layout variability since they are sourced from scientific article repositories such as PubMed and arXiv only. Consequently, the accuracy of the layout segmentation drops significantly when these models are applied on more chal…
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated…
Fudan University（复旦大学）；East China Normal University（华东师范大学）；Videt Lab（Videt实验室）；Zhongshan Hospital, Fudan University（复旦大学附属中山医院）
Document layout analysis (DLA) plays an important role in information extraction and document understanding. At present, document layout analysis has reached a milestone achievement, however, document layout analysis of non-Manhattan is still a challenge. In this paper, we propose an image layer modeling method to tackle this challenge. To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD. As far as we know, FPD is the first manually-labeled non-Manhattan layout fine-grained segmentation dataset. To …
PRHLT Research Center（PRHLT研究中心）；Universitat Politècnica de València（瓦伦西亚理工大学）
Document Layout Analysis is a fundamental step in Handwritten Text Processing systems, from the extraction of the text lines to the type of zone it belongs to. We present a system based on artificial neural networks which is able to determine not only the baselines of text lines present in the document, but also performs geometric and logic layout analysis of the document. Experiments in three different datasets demonstrate the potential of the method and show competitive results with respect to state-of-the-art methods.
KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document
National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP) University of Science and Technology of China（国家语信息处理语音工程研究中心（NERC-SLIP）大学科学技术大学）
University of California, Los Angeles（加州大学洛杉矶分校）；Google Research（谷歌研究院）
Document layout comprises both structural and visual (eg. font-sizes) information that is vital but often ignored by machine learning models. The few existing models which do use layout information only consider textual contents, and overlook the existence of contents in other modalities such as images. Additionally, spatial interactions of presented contents in a layout were never really fully exploited. To bridge this gap, we parse a document into content blocks (eg. text, table, image) and propose a novel layout-aware multimodal hierarchical framework, LAMPreT, to model the blocks and the w…
PRHLT Research Center（PRHLT研究中心）；Universitat Politècnica de València（瓦伦西亚理工大学）
Automatically recognizing the layout of handwritten documents is an important step towards useful extraction of information from those documents. The most common application is to feed downstream applications such as automatic text recognition and keyword spotting; however, the recognition of the layout also helps to establish relationships between elements in the document which allows to enrich the information that can be extracted. Most of the modern document layout analysis systems are designed to address only one part of the document layout problem, namely: baseline detection or region seg…
Hikvision Research Institute（海康威视研究院）；Zhejiang University（浙江大学）
Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to the understanding process. Though many works have been proposed to exploit the above information, they show unsatisfactory results. NLP-based methods model layout analysis as a sequence labeling task and show insufficient capabilities in layout modeling. CV-based methods model layout analysis as a detection or segmentation task, but bear limitations of inefficient modality fusion and lack of relation modeling between l…
Extraction of text regions and individual text lines from historic documents is necessary for automatic transcription. We propose extending a CNN-based text baseline detection system by adding line height and text block boundary predictions to the model output, allowing the system to extract more comprehensive layout information. We also show that pixel-wise text orientation prediction can be used for processing documents with multiple text orientations. We demonstrate that the proposed method performs well on the cBAD baseline detection dataset. Additionally, we benchmark the method on newly …
M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
South China University of Technology（华南理工大学）；Huawei Cloud Computing Technologies Co., Ltd.（华为云计算技术有限公司）；IntSig Information Co., Ltd.（合合信息科技股份有限公司）
Digitization of newspapers is of interest for many reasons including preservation of history, accessibility and search ability, etc. While digitization of documents such as scientific articles and magazines is prevalent in literature, one of the main challenges for digitization of newspaper lies in its complex layout (e.g. articles spanning multiple columns, text interrupted by images) analysis, which is necessary to preserve human read-order. This work provides a major breakthrough in the digitization of newspapers on three fronts: first, releasing a dataset of 3000 fully-annotated, real-worl…
Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale. One major hurdle is the lack of large datasets for training robust models. In particular, little training data exist for Asian languages. To this end, we present HJDataset, a Large Dataset of Historical Japanese Documents with Complex Layouts. It contains over 250,000 layout element annotations of seven types. In addition to bounding boxes and masks of the content regions, it also includes the hierarchical s…
South China University of Technology（华南理工大学）；Alibaba Group（阿里巴巴集团）
In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named character branch and layout branch are added behind the feature extraction network. The character branch localizes individual characters in a document image and recognizes them simultaneously. Then we adopt a post-processing method to group them into text lines. The layout branch based on fully convolutional network outputs a binary mask. We then use Hough transform for line detection on the binary mask and combine …
In this paper, we present a novel neural graph matching approach applied to document comparison. Document comparison is a common task in the legal and financial industries. In some cases, the most important differences may be the addition or omission of words, sentences, clauses, or paragraphs. However, it is a challenging task without recording or tracing whole edited process. Under many temporal uncertainties, we explore the potentiality of our approach to proximate the accurate comparison to make sure which element blocks have a relation of edition with others. In beginning, we apply a docu…
PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of the Chinese Academy of Sciences（中国科学院大学）；Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd.（中科创达福元人工智能实验室）；Columbia University（哥伦比亚大学）
This paper presents an open tool for standardizing the evaluation process of the layout analysis task of document images at pixel level. We introduce a new evaluation tool that is both available as a standalone Java application and as a RESTful web service. This evaluation tool is free and open-source in order to be a common tool that anyone can use and contribute to. It aims at providing as many metrics as possible to investigate layout analysis predictions, and also provide an easy way of visualizing the results. This tool evaluates document segmentation at pixel level, and support multi-lab…
ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Fanyu AI Laboratory, Zhongke Fanyu Technology Company Ltd.（中科泛宇人工智能实验室，中科泛宇科技有限公司）
East China Normal University（华东师范大学）；Videt Tech Ltd.（维迪特科技有限公司）
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval. However, it is a challenge to build a DLA system because the training data is very limited and lacks an efficient model. In this paper, we propose an end-to-end united network named Dynamic Residual Fusion Network (DRFN) for the DLA task. Specifically, we design a dynamic residual feature fusion module which can fully utilize low-dimensional information a…
Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasets
Insiders Technologies GmbH（Insiders Technologies 有限公司）；DFKI – German Research Center for Artificial Intelligence（德国人工智能研究中心）；RPTU – University Kaiserslautern-Landau（凯泽斯劳滕-兰道大学）
We present an approach for adapting convolutional neural networks for object recognition and classification to scientific literature layout detection (SLLD), a shared subtask of several information extraction problems. Scientific publications contain multiple types of information sought by researchers in various disciplines, organized into an abstract, bibliography, and sections documenting related work, experimental methods, and results; however, there is no effective way to extract this information due to their diverse layout. In this paper, we present a novel approach to developing an end-t…
Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning
Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University（浙江可感知与智能系统重点实验室，浙江大学）；Alibaba Group（阿里巴巴集团）；Shanghai AI Laboratory（上海人工智能实验室）
