PaddleOCR 3.0 Technical Report
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909679012020224 |
|---|---|
| author | Cui, Cheng Sun, Ting Lin, Manhui Gao, Tingquan Zhang, Yubo Liu, Jiaxuan Wang, Xueqing Zhang, Zelun Zhou, Changda Liu, Hongen Zhang, Yue Lv, Wenyu Huang, Kui Zhang, Yichao Zhang, Jing Zhang, Jun Liu, Yi Yu, Dianhai Ma, Yanjun |
| author_facet | Cui, Cheng Sun, Ting Lin, Manhui Gao, Tingquan Zhang, Yubo Liu, Jiaxuan Wang, Xueqing Zhang, Zelun Zhou, Changda Liu, Hongen Zhang, Yue Lv, Wenyu Huang, Kui Zhang, Yichao Zhang, Jing Zhang, Jun Liu, Yi Yu, Dianhai Ma, Yanjun |
| contents | This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three major solutions: (1) PP-OCRv5 for multilingual text recognition, (2) PP-StructureV3 for hierarchical document parsing, and (3) PP-ChatOCRv4 for key information extraction. Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs. In addition to offering a high-quality OCR model library, PaddleOCR 3.0 provides efficient tools for training, inference, and deployment, supports heterogeneous hardware acceleration, and enables developers to easily build intelligent document applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05595 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PaddleOCR 3.0 Technical Report Cui, Cheng Sun, Ting Lin, Manhui Gao, Tingquan Zhang, Yubo Liu, Jiaxuan Wang, Xueqing Zhang, Zelun Zhou, Changda Liu, Hongen Zhang, Yue Lv, Wenyu Huang, Kui Zhang, Yichao Zhang, Jing Zhang, Jun Liu, Yi Yu, Dianhai Ma, Yanjun Computer Vision and Pattern Recognition This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three major solutions: (1) PP-OCRv5 for multilingual text recognition, (2) PP-StructureV3 for hierarchical document parsing, and (3) PP-ChatOCRv4 for key information extraction. Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs. In addition to offering a high-quality OCR model library, PaddleOCR 3.0 provides efficient tools for training, inference, and deployment, supports heterogeneous hardware acceleration, and enables developers to easily build intelligent document applications. |
| title | PaddleOCR 3.0 Technical Report |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.05595 |