# PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

arXiv: https://arxiv.org/abs/2606.13108 · HTML: https://mlsanity.com/paper/2606.13108/

## Key facts

- Cited by 14 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 17 of its 20 references that are in the map.
- First posted on arXiv 11 Jun 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, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System](https://mlsanity.com/paper/2206.03001/) (2022)
- [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://mlsanity.com/paper/1806.00926/) (2018)
- [GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition](https://mlsanity.com/paper/2002.01276/) (2020)
- [PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System](https://mlsanity.com/paper/2109.03144/) (2021)
- [PP-LCNet: A Lightweight CPU Convolutional Neural Network](https://mlsanity.com/paper/2109.15099/) (2021)
- [PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks](https://mlsanity.com/paper/2603.24373/) (2026)

## Built on by (most cited first, 14 of 14)

- [Exploring the Performance Frontier of Compact Unified Image Generation Models](https://mlsanity.com/paper/2608.20334/) (2026)
- [Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications](https://mlsanity.com/paper/2607.00978/) (2026)
- [All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts](https://mlsanity.com/paper/2609.24058/) (2026)
- [SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks](https://mlsanity.com/paper/2608.12127/) (2026)
- [Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editing](https://mlsanity.com/paper/2609.08657/) (2026)
- [A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition](https://mlsanity.com/paper/2609.20064/) (2026)
- [Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB](https://mlsanity.com/paper/2609.28360/) (2026)
- [Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering](https://mlsanity.com/paper/2609.34178/) (2026)
- [PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence](https://mlsanity.com/paper/2609.37712/) (2026)
- [HelixWorld: A Real-time Interactive Audio-Visual World Model](https://mlsanity.com/paper/2609.38123/) (2026)
- [NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video](https://mlsanity.com/paper/2610.01461/) (2026)
- [HarnessIR: Harnessing Multimodal Foundation Models for Universal Real-World Image Restoration](https://mlsanity.com/paper/2610.10133/) (2026)
- [TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering](https://mlsanity.com/paper/2610.19551/) (2026)
- [CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation](https://mlsanity.com/paper/2610.20603/) (2026)

## Abstract (arXiv)

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-OCRv6medium achieves 83.2% recognition accuracy and 86.2% detection Hmean, outperforming PP-OCRv5server 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× faster inference than PP-OCRv5mobile on Intel Xeon CPU while maintaining comparable accuracy.