OCR 与文档解析模型
查找适合图片、扫描 PDF、表格和复杂版面的 OCR 与文档解析能力。
先看主题地图，再进入选型
先区分文字识别、版面理解和完整文档解析，再按中文支持、表格能力、本地部署与吞吐量缩小候选范围。当前 KG 中部分 OCR 候选被归为 model，因此主题页不会只筛选 tool。
本页用于理解主题范围、发现候选和相关概念；准备按部署、预算或能力约束比较时，请进入上方的对应选型指南。
主题精选 KG 入口
这里是用于发现本主题的一组精选入口，不代表付费排名，也不等同于官方产品评测；需要完整语义召回和二层总结，请回到首页检索。
PP-OCRv6
1.5M-parameter OCR model presented for low-latency edge deployment.
机制Agentic OCR
A multi-stage process running OCR, layout detection, and post-processing as sepa
模型DeepSeek-OCR
来源摘要：🌟 Github 📥 Model Download 📄 Paper Link 📄 Arxiv Paper Link Explore the boundaries of visual-text compression.
模型DeepSeek-OCR-2
来源摘要：🌟 Github 📥 Model Download 📄 Paper Link 📄 Arxiv Paper Link Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8：
模型GLM-OCR
来源摘要：GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of la
模型GOT-OCR-2.0-hf
来源摘要：General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model - HF Transformers 🤗 implementation Haoran Wei*, Chenglong Liu*, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, Chunrui Han, Xiangyu Zhang
模型LaTeX_OCR_rec
Hugging Face 元数据记录：image-to-text；PaddleOCR；image input；text output。当前没有可读的模型卡片摘要，适用性仍需核验。
模型nemotron-ocr-v1
来源摘要：The Nemotron OCR v1 model is a state-of-the-art text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images. It integrates three core neural network modules: a detector for text region localization, a recognizer for transcription of detected regions, and a relational model for layout and structure analysis.
留下这个主题的使用反馈
留言会关联到当前主题页面，保留在 KG 之外，其他访客也可以浏览和点赞。无需登录，不人工审核。