PP-OCRv6: 从1.5M到34.5M参数，在OCR任务上超越十亿级视觉语言模型
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
AI总结：
提出轻量级OCR系统PP-OCRv6，通过统一MetaFormer架构和结构化重参数化，在服务器到边缘设备上以少数量级参数超越十亿级VLM，中模型识别准确率83.2%，检测Hmean 86.2%。
摘要：
视觉语言模型（VLM）在通用视觉语言任务上取得了令人印象深刻的结果，但在应用于专用OCR场景时，它们存在幻觉、定位不精确和计算成本过高的问题。本文提出PP-OCRv6，一个轻量级OCR系统，结合了架构创新和数据中心优化。PP-OCRv6围绕统一的MetaFormer风格构建块重新设计了骨干网络、检测颈和识别颈，采用结构化重参数化，将空间token混合与通道混合解耦，并通过任务特定的步长配置支持两个任务。三个模型层级（中、小、微）共享相同的构建块原语，覆盖从服务器到边缘的部署场景。在我们的内部基准测试中，PP-OCRv6_medium实现了83.2%的识别准确率和86.2%的检测Hmean，分别比PP-OCRv5_server高出+5.1%和+4.6%，同时以数量级更少的参数超越了Qwen3-VL-235B、GPT-5.5和Gemini-3.1-Pro。微层级在Intel Xeon CPU上实现了比PP-OCRv5_mobile快3.9倍的推理速度，同时保持相当的准确率。
英文摘要：
Vision-Language Models (VLMs) have achieved impressive results on general vision-language tasks, yet they suffer from hallucination, imprecise localization, and prohibitive computational cost when applied to dedicated OCR scenarios. This paper presents PP-OCRv6, a lightweight OCR system that combines architectural innovation with data-centric optimization. PP-OCRv6 redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization, decoupling spatial token mixing from channel mixing and supporting both tasks through task-specific stride configurations. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. On our in-house benchmarks, PP-OCRv6_medium achieves 83.2% recognition accuracy and 86.2% detection Hmean, outperforming PP-OCRv5_server by +5.1% and +4.6% respectively while surpassing Qwen3-VL-235B, GPT-5.5, and Gemini-3.1-Pro with orders of magnitude fewer parameters. The tiny tier achieves 3.9$\times$ faster inference than PP-OCRv5_mobile on Intel Xeon CPU while maintaining comparable accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
