홈 › Papers

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

2024-12-10 · CVPR 2025 1 · Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, Jin Shi, Fan Wu, Pei Chu, Minghao Liu, Zhenxiang Li, Chao Xu, Bo Zhang, Botian Shi, Zhongying Tu, Conghui He

Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have not been fairly and comprehensively evaluated due to the narrow coverage of document types and the simplified, unrealistic evaluation procedures in existing benchmarks. To address these gaps, we introduce OmniDocBench, a novel benchmark featuring high-quality annotations across nine document sources, including academic papers, textbooks, and more challenging cases such as handwritten notes and densely typeset newspapers. OmniDocBench supports flexible, multi-level evaluations--ranging from an end-to-end assessment to the task-specific and attribute--based analysis using 19 layout categories and 15 attribute labels. We conduct a thorough evaluation of both pipeline-based methods and end-to-end vision-language models, revealing their strengths and weaknesses across different document types. OmniDocBench sets a new standard for the fair, diverse, and fine-grained evaluation in document parsing. Dataset and code are available at https://github.com/opendatalab/OmniDocBench.

📄 PDF Abstract BibTeX arXiv:2412.07626

Code (1)

opendatalab/OmniDocBench 공식 구현 paddle

Tasks

AttributeBenchmarkingDiversityRAGRetrieval-augmented Generation

DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation

2025-11-23 · Yongkun Du, Pinxuan Chen, Xuye Ying, Zhineng Chen arxiv

The advent of Multimodal Large Language Models (MLLMs) has unlocked the potential for end-to-end document parsing and translation. However, prevailing benchmarks such as OmniDocBench and DITrans are dominated by pristine…

NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents

2026-08-13 · Peng Cai, Zhaofan Zou, Shifa Liu, Yikun Wang 외 arxiv

Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have significantly advanced document parsing. However, exis…

Representation Learning

Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild

2026-03-04 · Changda Zhou, Ziyue Gao, Xueqing Wang, Tingquan Gao 외 arxiv

While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlle…

Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting

2026-02-05 · Hao Feng, Wei Shi, Ke Zhang, Xiang Fei 외 arxiv

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing user…

Attribute Extraction

Efficient Document Parsing via Parallel Token Prediction

2026-03-16 · Lei Li, Ze Zhao, Meng Li, Zhongwang Lun 외 arxiv

Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs creates a significant bottleneck, severely …