mlsanityData to 14 Oct 2026

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

arXiv 2206.03001 ↗First posted 7 Jun 2022cs.CVcited by 106

Not on the map. Why?

Cited by 22 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

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.

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

15 of 22 references.

References · 15

  1. 2017Squeeze-and-Excitation Networkscited by 4,789
  2. 2018Path Aggregation Network for Instance Segmentationcited by 798
  3. 2017Deep Mutual Learningcited by 628
  4. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  5. 2021ICDAR2019 Competition on Scanned Receipt OCR and Information Extractioncited by 256
  6. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 214
  7. 2020PP-OCR: A Practical Ultra Lightweight OCR Systemcited by 151
  8. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 139
  9. 2017ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)cited by 105
  10. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 88
  11. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
  12. 2020GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognitioncited by 52
3 more
  1. 2021PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR Systemcited by 39
  2. 2021PP-LCNet: A Lightweight CPU Convolutional Neural Networkcited by 27
  3. 2019Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learningcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 30; 2025: 42; 2026: 26.

106 papers.

Sort:

By area:

  1. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  2. 2024CogVLM2: Visual Language Models for Image and Video Understandingcited by 217
  3. 2023AnyText: Multilingual Visual Text Generation And Editingcited by 170
  4. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
  5. 2025PaddleOCR 3.0 Technical Reportcited by 143
  6. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 87
  7. 2024AnyText2: Visual Text Generation and Editing With Customizable Attributescited by 53
  8. 2025FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editingcited by 46
  9. 2025EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answeringcited by 44
  10. 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Modelscited by 34
  11. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 32
  12. 2024GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Modelscited by 29
38 more
  1. 2025CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughnesscited by 25
  2. 2025OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoningcited by 25
  3. 2024SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognitioncited by 24
  4. 2023Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Predictioncited by 23
  5. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 22
  6. 2025UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAGcited by 21
  7. 2023Modeling Entities as Semantic Points for Visual Information Extraction in the Wildcited by 20
  8. 2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understandingcited by 20
  9. 2023Context Perception Parallel Decoder for Scene Text Recognitioncited by 19
  10. 2024Instruction-Guided Scene Text Recognitioncited by 17
  11. 2025Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsingcited by 17
  12. 2024First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blendingcited by 16
  13. 2025LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesiscited by 15
  14. 2025SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generationcited by 15
  15. 2023Responsible Task Automation: Empowering Large Language Models as Responsible Task Automatorscited by 14
  16. 2024CharGen: High Accurate Character-Level Visual Text Generation Model with MultiModal Encodercited by 14
  17. 2025Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agentscited by 14
  18. 2026PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Taskscited by 14
  19. 2024Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generationcited by 13
  20. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patternscited by 13
  21. 2024FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queriescited by 12
  22. 2024Out of Length Text Recognition with Sub-String Matchingcited by 11
  23. 2024ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spottingcited by 10
  24. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Modelcited by 10
  25. 2024Bridging the Gap Between End-to-End and Two-Step Text Spottingcited by 9
  26. 2026PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Taskscited by 9
  27. 2023Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approachcited by 8
  28. 2024TextSSR: Diffusion-based Data Synthesis for Scene Text Recognitioncited by 8
  29. 2024MindGuard: Towards Accessible and Sitgma-free Mental Health First Aid via Edge LLMcited by 7
  30. 2025RepText: Rendering Visual Text via Replicatingcited by 7
  31. 2025VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Modelscited by 6
  32. 2026SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generationcited by 6
  33. 2024Typographic Text Generation with Off-the-Shelf Diffusion Modelcited by 5
  34. 2024TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Controlcited by 5
  35. 2025TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmarkcited by 5
  36. 2025Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challengescited by 5
  37. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 5
  38. 2026StyleTextGen: Style-Conditioned Multilingual Scene Text Generationcited by 5

50 most cited of 106 All 106 (JSON)