NaviDC-OCR：跨越數位與相機拍攝文檔的文檔解析導航

摘要

文檔解析旨在將非結構化文檔轉換為結構化且機器可讀的表示形式。近年來，視覺-語言模型（VLMs）的進展顯著推進了文檔解析技術的發展。然而，現有方法仍然面臨兩大挑戰。首先，基於解耦的視覺-語言模型方法高度依賴精確的版面分析，而相機拍攝文檔中的幾何變形可能引入級聯誤差。其次，儘管基於端到端的視覺-語言模型方法減輕了對顯式版面檢測的依賴，但它們在高解析度場景中常常存在冗餘生成、幻覺以及結構推理不足的問題。為應對這些挑戰，我們提出了 NaviDC-OCR，一個統一的文檔解析框架。NaviDC-OCR 引入了變形感知學習，將幾何感知融入視覺-語言模型中，並針對複雜版面表示提出了自適應採樣機制。此外，我們開發了一種內容-結構解耦學習策略，以顯式建模公式語法和表格結構，從而實現更有效的結構化表示學習。大量實驗表明，NaviDC-OCR 在多個文檔解析基準測試中均取得了最先進的性能。它在 OmniDocBench v1.6、Wild-OmniDocBench 和 PureDocBench 上分別獲得了 96.87、88.53 和 78.41 的總體得分，並在 ICDAR 2026 Sci-ImageMiner 挑戰賽中排名第一。這些結果驗證了 NaviDC-OCR 在複雜文檔解析場景中的有效性和泛化能力。

English

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.