# Scene Text Image Super-Resolution in the Wild

arXiv: https://arxiv.org/abs/2005.03341 · HTML: https://mlsanity.com/paper/2005.03341/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 30 of 63)

- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [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)
- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition](https://mlsanity.com/paper/2207.00193/) (2022)
- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [Text Prior Guided Scene Text Image Super-resolution](https://mlsanity.com/paper/2106.15368/) (2021)
- [A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution](https://mlsanity.com/paper/2203.09388/) (2022)
- [Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution](https://mlsanity.com/paper/2112.08171/) (2021)
- [Self-supervised Character-to-Character Distillation for Text Recognition](https://mlsanity.com/paper/2211.00288/) (2022)
- [NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results](https://mlsanity.com/paper/2104.10781/) (2021)
- [C3-STISR: Scene Text Image Super-resolution with Triple Clues](https://mlsanity.com/paper/2204.14044/) (2022)
- [Diffusion-based Blind Text Image Super-Resolution](https://mlsanity.com/paper/2312.08886/) (2023)
- [Learning Generative Structure Prior for Blind Text Image Super-resolution](https://mlsanity.com/paper/2303.14726/) (2023)
- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [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)
- [Towards the Unseen: Iterative Text Recognition by Distilling from Errors](https://mlsanity.com/paper/2107.12081/) (2021)
- [SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition](https://mlsanity.com/paper/2207.10256/) (2022)
- [TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2308.06743/) (2023)
- [OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities](https://mlsanity.com/paper/2507.15085/) (2025)
- [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)
- [Text Image Inpainting via Global Structure-Guided Diffusion Models](https://mlsanity.com/paper/2401.14832/) (2024)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders](https://mlsanity.com/paper/2506.04641/) (2025)
- [Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.13317/) (2023)
- [Text-Aware Image Restoration with Diffusion Models](https://mlsanity.com/paper/2506.09993/) (2025)

## Abstract (arXiv)

Low-resolution text images are often seen in natural scenes such as documents captured by mobile phones. Recognizing low-resolution text images is challenging because they lose detailed content information, leading to poor recognition accuracy. An intuitive solution is to introduce super-resolution (SR) techniques as pre-processing. However, previous single image super-resolution (SISR) methods are trained on synthetic low-resolution images (e.g.Bicubic down-sampling), which is simple and not suitable for real low-resolution text recognition. To this end, we pro-pose a real scene text SR dataset, termed TextZoom. It contains paired real low-resolution and high-resolution images which are captured by cameras with different focal length in the wild. It is more authentic and challenging than synthetic data, as shown in Fig. 1. We argue improv-ing the recognition accuracy is the ultimate goal for Scene Text SR. In this purpose, a new Text Super-Resolution Network termed TSRN, with three novel modules is developed. (1) A sequential residual block is proposed to extract the sequential information of the text images. (2) A boundary-aware loss is designed to sharpen the character boundaries. (3) A central alignment module is proposed to relieve the misalignment problem in TextZoom. Extensive experiments on TextZoom demonstrate that our TSRN largely improves the recognition accuracy by over 13%of CRNN, and by nearly 9.0% of ASTER and MORAN compared to synthetic SR data. Furthermore, our TSRN clearly outperforms 7 state-of-the-art SR methods in boosting the recognition accuracy of LR images in TextZoom. For example, it outperforms LapSRN by over 5% and 8%on the recognition accuracy of ASTER and CRNN. Our results suggest that low-resolution text recognition in the wild is far from being solved, thus more research effort is needed.