# Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution

arXiv: https://arxiv.org/abs/2112.08171 · HTML: https://mlsanity.com/paper/2112.08171/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [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)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Reading Text in the Wild with Convolutional Neural Networks](https://mlsanity.com/paper/1412.1842/) (2014)
- [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://mlsanity.com/paper/1806.00926/) (2018)
- [Scene Text Image Super-Resolution in the Wild](https://mlsanity.com/paper/2005.03341/) (2020)
- [Text Prior Guided Scene Text Image Super-resolution](https://mlsanity.com/paper/2106.15368/) (2021)
- [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021)
- [AutoSTR: Efficient Backbone Search for Scene Text Recognition](https://mlsanity.com/paper/2003.06567/) (2020)
- [Binary Document Image Super Resolution for Improved Readability and OCR Performance](https://mlsanity.com/paper/1812.02475/) (2018)

## Built on by (most cited first, 28 of 28)

- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [C3-STISR: Scene Text Image Super-resolution with Triple Clues](https://mlsanity.com/paper/2204.14044/) (2022)
- [Learning Generative Structure Prior for Blind Text Image Super-resolution](https://mlsanity.com/paper/2303.14726/) (2023)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [A Benchmark for Chinese-English Scene Text Image Super-resolution](https://mlsanity.com/paper/2308.03262/) (2023)
- [Improving Scene Text Image Super-resolution via Dual Prior Modulation Network](https://mlsanity.com/paper/2302.10414/) (2023)
- [Scene Text Image Super-resolution based on Text-conditional Diffusion Models](https://mlsanity.com/paper/2311.09759/) (2023)
- [TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2308.06743/) (2023)
- [Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks](https://mlsanity.com/paper/2210.06924/) (2022)
- [Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement](https://mlsanity.com/paper/2307.09749/) (2023)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.13317/) (2023)
- [Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2309.08919/) (2023)
- [Weakly-Supervised Text Instance Segmentation](https://mlsanity.com/paper/2303.10848/) (2023)
- [Deep Image Compression Using Scene Text Quality Assessment](https://mlsanity.com/paper/2305.11373/) (2023)
- [PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.17955/) (2023)
- [One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer](https://mlsanity.com/paper/2308.02770/) (2023)
- [Enhanced Generative Structure Prior for Chinese Text Image Super-resolution](https://mlsanity.com/paper/2508.07537/) (2025)
- [Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration](https://mlsanity.com/paper/2512.08922/) (2025)
- [Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correction](https://mlsanity.com/paper/2307.16253/) (2023)
- [Task-driven single-image super-resolution reconstruction of document scans](https://mlsanity.com/paper/2407.08993/) (2024)
- [NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior](https://mlsanity.com/paper/2504.00410/) (2025)
- [DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2603.14207/) (2026)
- [HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution](https://mlsanity.com/paper/2307.16410/) (2023)
- [A Lightweight Multi-Module Fusion Approach for Korean Character Recognition](https://mlsanity.com/paper/2504.05770/) (2025)
- [GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?](https://mlsanity.com/paper/2510.26339/) (2025)
- [TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution](https://mlsanity.com/paper/2609.29240/) (2026)
- [Think Before You Restore: Risk-Aware Manchu Manuscript Restoration with Stroke-Guided Attention](https://mlsanity.com/paper/2609.36243/) (2026)

## Abstract (arXiv)

In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have been proposed to tackle this problem, they usually treat text images as general images while ignoring the fact that the visual quality of strokes (the atomic unit of text) plays an essential role for text recognition. According to Gestalt Psychology, humans are capable of composing parts of details into the most similar objects guided by prior knowledge. Likewise, when humans observe a low-resolution text image, they will inherently use partial stroke-level details to recover the appearance of holistic characters. Inspired by Gestalt Psychology, we put forward a Stroke-Aware Scene Text Image Super-Resolution method containing a Stroke-Focused Module (SFM) to concentrate on stroke-level internal structures of characters in text images. Specifically, we attempt to design rules for decomposing English characters and digits at stroke-level, then pre-train a text recognizer to provide stroke-level attention maps as positional clues with the purpose of controlling the consistency between the generated super-resolution image and high-resolution ground truth. The extensive experimental results validate that the proposed method can indeed generate more distinguishable images on TextZoom and manually constructed Chinese character dataset Degraded-IC13. Furthermore, since the proposed SFM is only used to provide stroke-level guidance when training, it will not bring any time overhead during the test phase. Code is available at https://github.com/FudanVI/FudanOCR/tree/main/text-gestalt.