PP-OCRv6用轻量设计超越百亿参数大模型，实现高精度文字识别。
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
- 采用统一的MetaFormer块与结构重参数化，分离空间与通道混合
- 中型版识别准确率83.2%，检测Hmean达86.2%，性能超前代5%以上
- 小尺寸模型推理快3.9倍，适合边缘部署，适合追求效率的开发者
视觉语言模型（VLMs）在通用任务上表现优异，但在专用文字识别场景中存在幻觉、定位不准和计算成本过高等问题。本文提出轻量级OCR系统PP-OCRv6，通过架构创新与数据驱动优化相结合。该系统重构了主干网络、检测颈部与识别颈部，采用统一的MetaFormer风格模块，结合结构重参数化，解耦空间特征混合与通道特征混合，并通过任务特异的步长配置支持两类任务。三个模型层级（中、小、极小）共享相同的基础模块，覆盖从服务器到边缘设备的部署需求。在自建基准测试中，PP-OCRv6_medium达到83.2%识别准确率和86.2%检测Hmean，相比PP-OCRv5_server分别提升+5.1%和+4.6%，且在参数量远低于Qwen3-VL-235B、GPT-5.5和Gemini-3.1-Pro的情况下仍全面超越。极小版模型在Intel Xeon CPU上的推理速度比PP-OCRv5_mobile快3.9倍，同时保持相近准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。