# PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks arXiv: https://arxiv.org/abs/2603.24373 ยท HTML: https://mlsanity.com/paper/2603.24373/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. - Builds on 22 of its 29 references that are in the map. - First posted on arXiv 25 Mar 2026. ## Placed in - Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/) ## Builds on (most cited first, 22 of 22) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016) - [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022) - [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023) - [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020) - [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015) - [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023) - [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019) - [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021) - [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016) - [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022) - [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019) - [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023) - [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://mlsanity.com/paper/2103.06495/) (2021) - [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024) - [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020) - [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021) - [PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System](https://mlsanity.com/paper/2206.03001/) (2022) - [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022) - [GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition](https://mlsanity.com/paper/2002.01276/) (2020) - [PP-LCNet: A Lightweight CPU Convolutional Neural Network](https://mlsanity.com/paper/2109.15099/) (2021) ## Built on by (most cited first, 9 of 9) - [PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks](https://mlsanity.com/paper/2606.13108/) (2026) - [GMO-E2DIT: Grounded Multi-Operation Editing for E-Commerce Images](https://mlsanity.com/paper/2607.00920/) (2026) - [The Character Error Vector: Decomposable errors for page-level OCR evaluation](https://mlsanity.com/paper/2604.06160/) (2026) - [Rethinking RAG in Long Videos: What to Retrieve and How to Use It?](https://mlsanity.com/paper/2606.13141/) (2026) - [OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations](https://mlsanity.com/paper/2609.02149/) (2026) - [VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes](https://mlsanity.com/paper/2609.06652/) (2026) - [HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM](https://mlsanity.com/paper/2609.17168/) (2026) - [A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition](https://mlsanity.com/paper/2609.20064/) (2026) - [Stride: Scale-Aware Multi-Agent Evolutionary Refinement for Infographic Generation](https://mlsanity.com/paper/2610.13502/) (2026) ## Abstract (arXiv) The advent of "OCR 2.0" and large-scale vision-language models (VLMs) has set new benchmarks in text recognition. However, these unified architectures often come with significant computational demands, challenges in precise text localization within complex layouts, and a propensity for textual hallucinations. Revisiting the prevailing notion that model scale is the sole path to high accuracy, this paper introduces PP-OCRv5, a meticulously optimized, lightweight OCR system with merely 5 million parameters. We demonstrate that PP-OCRv5 achieves performance competitive with many billion-parameter VLMs on standard OCR benchmarks, while offering superior localization precision and reduced hallucinations. The cornerstone of our success lies not in architectural expansion but in a data-centric investigation. We systematically dissect the role of training data by quantifying three critical dimensions: data difficulty, data accuracy, and data diversity. Our extensive experiments reveal that with a sufficient volume of high-quality, accurately labeled, and diverse data, the performance ceiling for traditional, efficient two-stage OCR pipelines is far higher than commonly assumed. This work provides compelling evidence for the viability of lightweight, specialized models in the large-model era and offers practical insights into data curation for OCR. The source code and models are publicly available at https://github.com/PaddlePaddle/PaddleOCR.