DREAM: Document Reconstruction via End-to-end Autoregressive Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xin, Gong, Mingming, Wu, Yunfei, Dai, Jianxin, Guo, Antai, Jiang, Xinghua, Cao, Haoyu, Liu, Yinsong, Jiang, Deqiang, Sun, Xing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908440805244928
author Li, Xin
Gong, Mingming
Wu, Yunfei
Dai, Jianxin
Guo, Antai
Jiang, Xinghua
Cao, Haoyu
Liu, Yinsong
Jiang, Deqiang
Sun, Xing
author_facet Li, Xin
Gong, Mingming
Wu, Yunfei
Dai, Jianxin
Guo, Antai
Jiang, Xinghua
Cao, Haoyu
Liu, Yinsong
Jiang, Deqiang
Sun, Xing
contents Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document understanding models to generate predictions on distinct subtasks, subsequently integrating their results into a holistic document reconstruction format via heuristic principles. Nevertheless, these multi-stage methodologies are hindered by the phenomenon of error propagation, resulting in suboptimal performance. Furthermore, contemporary studies utilize generative models to extract the logical sequence of plain text, tables and mathematical expressions in an end-to-end process. However, this approach is deficient in preserving the information related to element layouts, which are vital for document reconstruction. To surmount these aforementioned limitations, we in this paper present an innovative autoregressive model specifically designed for document reconstruction, referred to as Document Reconstruction via End-to-end Autoregressive Model (DREAM). DREAM transmutes the text image into a sequence of document reconstruction in a comprehensive, end-to-end process, encapsulating a broader spectrum of document element information. In addition, we establish a standardized definition of the document reconstruction task, and introduce a novel Document Similarity Metric (DSM) and DocRec1K dataset for assessing the performance of the task. Empirical results substantiate that our methodology attains unparalleled performance in the realm of document reconstruction. Furthermore, the results on a variety of subtasks, encompassing document layout analysis, text recognition, table structure recognition, formula recognition and reading order detection, indicate that our model is competitive and compatible with various tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05805
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DREAM: Document Reconstruction via End-to-end Autoregressive Model
Li, Xin
Gong, Mingming
Wu, Yunfei
Dai, Jianxin
Guo, Antai
Jiang, Xinghua
Cao, Haoyu
Liu, Yinsong
Jiang, Deqiang
Sun, Xing
Computer Vision and Pattern Recognition
Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document understanding models to generate predictions on distinct subtasks, subsequently integrating their results into a holistic document reconstruction format via heuristic principles. Nevertheless, these multi-stage methodologies are hindered by the phenomenon of error propagation, resulting in suboptimal performance. Furthermore, contemporary studies utilize generative models to extract the logical sequence of plain text, tables and mathematical expressions in an end-to-end process. However, this approach is deficient in preserving the information related to element layouts, which are vital for document reconstruction. To surmount these aforementioned limitations, we in this paper present an innovative autoregressive model specifically designed for document reconstruction, referred to as Document Reconstruction via End-to-end Autoregressive Model (DREAM). DREAM transmutes the text image into a sequence of document reconstruction in a comprehensive, end-to-end process, encapsulating a broader spectrum of document element information. In addition, we establish a standardized definition of the document reconstruction task, and introduce a novel Document Similarity Metric (DSM) and DocRec1K dataset for assessing the performance of the task. Empirical results substantiate that our methodology attains unparalleled performance in the realm of document reconstruction. Furthermore, the results on a variety of subtasks, encompassing document layout analysis, text recognition, table structure recognition, formula recognition and reading order detection, indicate that our model is competitive and compatible with various tasks.
title DREAM: Document Reconstruction via End-to-end Autoregressive Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.05805