# PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System

arXiv: https://arxiv.org/abs/2206.03001 · HTML: https://mlsanity.com/paper/2206.03001/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 7 Jun 2022.

## Builds on (most cited first, 15 of 15)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [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)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019](https://mlsanity.com/paper/1907.00945/) (2019)
- [ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)](https://mlsanity.com/paper/1708.09585/) (2017)
- [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022)
- [What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels](https://mlsanity.com/paper/2103.04400/) (2021)
- [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)
- [Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning](https://mlsanity.com/paper/1909.07808/) (2019)

## Built on by (most cited first, 30 of 106)

- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://mlsanity.com/paper/2412.07626/) (2024)
- [PaddleOCR 3.0 Technical Report](https://mlsanity.com/paper/2507.05595/) (2025)
- [MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm](https://mlsanity.com/paper/2506.05218/) (2025)
- [AnyText2: Visual Text Generation and Editing With Customizable Attributes](https://mlsanity.com/paper/2411.15245/) (2024)
- [FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing](https://mlsanity.com/paper/2505.03329/) (2025)
- [EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering](https://mlsanity.com/paper/2502.07411/) (2025)
- [MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models](https://mlsanity.com/paper/2406.07594/) (2024)
- [FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution](https://mlsanity.com/paper/2411.18824/) (2024)
- [GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models](https://mlsanity.com/paper/2407.02252/) (2024)
- [CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness](https://mlsanity.com/paper/2502.14914/) (2025)
- [OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning](https://mlsanity.com/paper/2505.17163/) (2025)
- [SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition](https://mlsanity.com/paper/2411.15858/) (2024)
- [Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction](https://mlsanity.com/paper/2310.11016/) (2023)
- [Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters](https://mlsanity.com/paper/2311.11268/) (2023)
- [UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG](https://mlsanity.com/paper/2510.03663/) (2025)
- [Modeling Entities as Semantic Points for Visual Information Extraction in the Wild](https://mlsanity.com/paper/2303.13095/) (2023)
- [Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding](https://mlsanity.com/paper/2503.14140/) (2025)
- [Context Perception Parallel Decoder for Scene Text Recognition](https://mlsanity.com/paper/2307.12270/) (2023)
- [Instruction-Guided Scene Text Recognition](https://mlsanity.com/paper/2401.17851/) (2024)
- [Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing](https://mlsanity.com/paper/2510.15349/) (2025)
- [First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending](https://mlsanity.com/paper/2410.10168/) (2024)
- [LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis](https://mlsanity.com/paper/2503.21749/) (2025)
- [SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.21585/) (2025)
- [Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators](https://mlsanity.com/paper/2306.01242/) (2023)
- [CharGen: High Accurate Character-Level Visual Text Generation Model with MultiModal Encoder](https://mlsanity.com/paper/2412.17225/) (2024)
- [Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents](https://mlsanity.com/paper/2505.12632/) (2025)
- [PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks](https://mlsanity.com/paper/2606.13108/) (2026)

## Abstract (arXiv)

Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and accuracy, we proposed a practical ultra lightweight OCR system (PP-OCR), and an optimized version PP-OCRv2. In order to further improve the performance of PP-OCRv2, a more robust OCR system PP-OCRv3 is proposed in this paper. PP-OCRv3 upgrades the text detection model and text recognition model in 9 aspects based on PP-OCRv2. For text detector, we introduce a PAN module with large receptive field named LK-PAN, a FPN module with residual attention mechanism named RSE-FPN, and DML distillation strategy. For text recognizer, the base model is replaced from CRNN to SVTR, and we introduce lightweight text recognition network SVTR LCNet, guided training of CTC by attention, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML, and UIM to accelerate the model and improve the effect. Experiments on real data show that the hmean of PP-OCRv3 is 5% higher than PP-OCRv2 under comparable inference speed. All the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleOCR which is powered by PaddlePaddle.