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

Hugging Face Daily Papers Papers
document-parsing vision-language-models ocr machine-learning deformation-aware-learning benchmark

Summary

NaviDC-OCR is a unified vision-language framework that improves document parsing accuracy through deformation-aware learning and adaptive sampling, achieving state-of-the-art results on multiple benchmarks.

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, existing approaches still face two major challenges. First, decoupled VLM-based methods heavily rely on accurate layout analysis, where geometric distortions in camera-captured documents can introduce cascading errors. Second, although end-to-end VLM-based methods alleviate the dependence on explicit layout detection, they often suffer from redundant generation, hallucinations, and insufficient structural reasoning in high-resolution scenarios. To address these challenges, we propose NaviDC-OCR, a unified framework for document parsing. NaviDC-OCR introduces deformation-aware learning to incorporate geometric perception into VLMs and proposes an adaptive sampling mechanism for complex layout representation. Furthermore, a content-structure decoupled learning strategy is developed to explicitly model formula grammars and table structures, enabling more effective structured representation learning. Extensive experiments demonstrate that NaviDC-OCR achieves state-of-the-art performance across diverse document parsing benchmarks. It obtains overall scores of 96.87, 88.53 and 78.41 on OmniDocBench v1.6, Wild-OmniDocBench, and PureDocBench, respectively, and ranks first in the ICDAR 2026 Sci-ImageMiner Challenge. These results validate the effectiveness and generalization capability of NaviDC-OCR in complex document parsing scenarios.
Original Article
View Cached Full Text

Cached at: 08/18/26, 03:54 AM

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

Source: https://huggingface.co/papers/2608.12898

Abstract

NaviDC-OCR is a unified vision-language framework that integrates deformation-aware learning, adaptive layout sampling, and decoupled content-structure training to improve document parsing accuracy and structural reasoning.

Document parsingaims to transform unstructured documents into structured and machine-readable representations. Recent advances inVision-Language Models(VLMs) have significantly advanceddocument parsing. However, existing approaches still face two major challenges. First, decoupled VLM-based methods heavily rely on accurate layout analysis, where geometric distortions in camera-captured documents can introduce cascading errors. Second, although end-to-end VLM-based methods alleviate the dependence on explicit layout detection, they often suffer from redundant generation, hallucinations, and insufficient structural reasoning in high-resolution scenarios. To address these challenges, we propose NaviDC-OCR, a unified framework fordocument parsing. NaviDC-OCR introducesdeformation-aware learningto incorporate geometric perception into VLMs and proposes anadaptive sampling mechanismfor complex layout representation. Furthermore, acontent-structure decoupled learningstrategy is developed to explicitly modelformula grammarsandtable structures, enabling more effective structured representation learning. Extensive experiments demonstrate that NaviDC-OCR achieves state-of-the-art performance across diversedocument parsingbenchmarks. It obtains overall scores of 96.87, 88.53 and 78.41 on OmniDocBench v1.6, Wild-OmniDocBench, and PureDocBench, respectively, and ranks first in the ICDAR 2026 Sci-ImageMiner Challenge. These results validate the effectiveness and generalization capability of NaviDC-OCR in complexdocument parsingscenarios.

View arXiv pageView PDFGitHub17Add to collection

Get this paper in your agent:

hf papers read 2608\.12898

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### StarDoc-AI/NaviDC-OCR Image-Text-to-Text• 1B• Updated14 minutes ago • 3

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.12898 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.12898 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

MonkeyOCRv2: A Visual-Text Foundation Model for Document AI

Hugging Face Daily Papers

MonkeyOCRv2 is a visual-text foundation model for document AI, pretrained on a large corpus of 113 million images across 17 languages using joint image-to-text generation and pixel-level document reconstruction. It achieves state-of-the-art results on document parsing and understanding tasks, outperforming previous models with a smaller vision encoder.

baidu/Unlimited-OCR

Hugging Face Models Trending

Baidu releases Unlimited-OCR, a new model for one-shot long-horizon document parsing, building on Deepseek-OCR. It supports single image and multi-page/PDF parsing via Hugging Face Transformers and SGLang.

dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model

Papers with Code Trending

This paper presents dots.ocr, a unified Vision-Language Model that jointly learns layout detection, text recognition, and relational understanding for multilingual document layout parsing. It achieves state-of-the-art results on OmniDocBench and introduces the XDocParse benchmark spanning 126 languages.