The development of large vision language models drives the demand for managing, and applying massive amounts of multimodal data, making OCR technology, which extracts information from visual images, increasingly popular. However, existing OCR methods primarily focus on recognizing text elements from images or scanned documents (\textbf{Text-centric OCR}), neglecting the identification of visual elements from visually information-dense image sources (\textbf{Vision-centric OCR}), such as charts, web pages and science plots. In reality, these visually information-dense images are widespread on the internet and have significant real-world application value, such as data visualization and web page analysis. In this technical report, we propose \textbf{OCRVerse}, the first holistic OCR method in end-to-end manner that enables unified text-centric OCR and vision-centric OCR. To this end, we constructe comprehensive data engineering to cover a wide range of text-centric documents, such as newspapers, magazines and books, as well as vision-centric rendered composites, including charts, web pages and scientific plots. Moreover, we propose a two-stage SFT-RL multi-domain training method for OCRVerse. SFT directly mixes cross-domain data to train and establish initial domain knowledge, while RL focuses on designing personalized reward strategies for the characteristics of each domain. Specifically, since different domains require various output formats and expected outputs, we provide sufficient flexibility in the RL stage to customize flexible reward signals for each domain, thereby improving cross-domain fusion and avoiding data conflicts. Experimental results demonstrate the effectiveness of OCRVerse, achieving competitive results across text-centric and vision-centric data types, even comparable to large-scale open-source and closed-source models.

翻译：大型视觉语言模型的发展推动了对海量多模态数据管理及应用的需求，使得从视觉图像中提取信息的OCR技术日益普及。然而，现有的OCR方法主要聚焦于从图像或扫描文档中识别文本元素（**以文本为中心的OCR**），而忽略了从视觉信息密集的图像源（**以视觉为中心的OCR**）中识别视觉元素，例如图表、网页和科学绘图。实际上，这类视觉信息密集的图像在互联网上广泛存在，并具有重要的实际应用价值，如数据可视化和网页分析。在本技术报告中，我们提出了**OCRVerse**，这是首个以端到端方式实现统一文本中心OCR与视觉中心OCR的全方位OCR方法。为此，我们构建了全面的数据工程，覆盖了广泛的文本中心文档（如报纸、杂志和书籍）以及视觉中心渲染合成图像（包括图表、网页和科学绘图）。此外，我们为OCRVerse提出了一种两阶段的SFT-RL多领域训练方法。SFT直接混合跨领域数据进行训练以建立初始领域知识，而RL则针对各领域特点设计个性化奖励策略。具体而言，由于不同领域需要不同的输出格式和预期输出，我们在RL阶段提供了充分的灵活性，为每个领域定制灵活的奖励信号，从而提升跨领域融合能力并避免数据冲突。实验结果表明OCRVerse的有效性，其在文本中心与视觉中心数据类型上均取得了具有竞争力的结果，甚至可与大规模开源及闭源模型相媲美。