mlsanityData to 14 Oct 2026

SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models

arXiv 2107.09313 ↗First posted 20 Jul 2021cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

For successful scene text recognition (STR) models, synthetic text image generators have alleviated the lack of annotated text images from the real world. Specifically, they generate multiple text images with diverse backgrounds, font styles, and text shapes and enable STR models to learn visual patterns that might not be accessible from manually annotated data. In this paper, we introduce a new synthetic text image generator, SynthTIGER, by analyzing techniques used for text image synthesis and integrating effective ones under a single algorithm. Moreover, we propose two techniques that alleviate the long-tail problem in length and character distributions of training data. In our experiments, SynthTIGER achieves better STR performance than the combination of synthetic datasets, MJSynth (MJ) and SynthText (ST). Our ablation study demonstrates the benefits of using sub-components of SynthTIGER and the guideline on generating synthetic text images for STR models. Our implementation is publicly available at https://github.com/clovaai/synthtiger.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 6 of its 21 references that are in the map. First posted on arXiv 20 Jul 2021.

Builds on

6 of 21 references.

References · 6

  1. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  2. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  3. 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
  4. 2018Scene Text Detection and Recognition: The Deep Learning Eracited by 114
  5. 2020UnrealText: Synthesizing Realistic Scene Text Images from the Unreal Worldcited by 43
  6. 2019SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worldscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 13; 2024: 9; 2025: 6; 2026: 9.

43 papers.

Sort:

By area:

  1. 2021OCR-free Document Understanding Transformercited by 407
  2. 2024SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Modelscited by 131
  3. 2023Improving Diffusion Models for Scene Text Editing with Dual Encoderscited by 45
  4. 2023DiffUTE: Universal Text Editing Diffusion Modelcited by 45
  5. 2023Revisiting Scene Text Recognition: A Data Perspectivecited by 45
  6. 2023DTrOCR: Decoder-only Transformer for Optical Character Recognitioncited by 40
  7. 2022Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminatorcited by 32
  8. 2022Self-supervised Implicit Glyph Attention for Text Recognitioncited by 25
  9. 2023ICDAR 2023 Competition on Hierarchical Text Detection and Recognitioncited by 23
  10. 2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 19
  11. 2026TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Renderingcited by 15
  12. 2023Hierarchical Text Spotter for Joint Text Spotting and Layout Analysiscited by 8
31 more
  1. 2024Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processingcited by 8
  2. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7
  3. 2022A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Datacited by 5
  4. 2022On Web-based Visual Corpus Construction for Visual Document Understandingcited by 5
  5. 2024TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Modelcited by 5
  6. 2024DocSynthv2: A Practical Autoregressive Modeling for Document Generationcited by 5
  7. 2023Analyzing Font Style Usage and Contextual Factors in Real Imagescited by 3
  8. 2024CREPE: Coordinate-Aware End-to-End Document Parsercited by 3
  9. 2023Weakly Supervised Scene Text Generation for Low-resource Languagescited by 2
  10. 2023Selective Scene Text Removalcited by 2
  11. 2023PSGText: Stroke-Guided Scene Text Editing with PSP Modulecited by 2
  12. 2024What Text Design Characterizes Book Genres?cited by 2
  13. 2024UnSupDLA: Towards Unsupervised Document Layout Analysiscited by 2
  14. 2025MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generationcited by 2
  15. 2026synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barriercited by 2
  16. 2026What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolutioncited by 2
  17. 2026GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scriptscited by 2
  18. 2026Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methodscited by 2
  19. 2022Character decomposition to resolve class imbalance problem in Hangul OCRcited by 1
  20. 2025Relaxed syntax modeling in Transformers for future-proof license plate recognitioncited by 1
  21. 2025Exploring OCR-augmented Generation for Bilingual VQAcited by 1
  22. 2026Towards Khmer Scene Document Layout Detectioncited by 1
  23. 2026DocAtlas: Multilingual Document Understanding Across 80+ Languagescited by 1
  24. 2023bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documentscited by 0
  25. 2023Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Modelscited by 0
  26. 2024Font Impression Estimation in the Wildcited by 0
  27. 2024Text Image Generation for Low-Resource Languages with Dual Translation Learningcited by 0
  28. 2025Syn3DTxt: Embedding 3D Cues for Scene Text Generationcited by 0
  29. 2025A Large-scale Dataset for Robust Complex Anime Scene Text Detectioncited by 0
  30. 2026LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitrationcited by 0
  31. 2026What Can Low Resource Languages Learn From Each Other?cited by 0