# NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior

arXiv: https://arxiv.org/abs/2504.00410 · HTML: https://mlsanity.com/paper/2504.00410/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [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)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://mlsanity.com/paper/2103.06495/) (2021)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://mlsanity.com/paper/2207.06966/) (2022)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [Self-Knowledge Distillation with Progressive Refinement of Targets](https://mlsanity.com/paper/2006.12000/) (2020)
- [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)
- [A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution](https://mlsanity.com/paper/2203.09388/) (2022)
- [A Multi-Object Rectified Attention Network for Scene Text Recognition](https://mlsanity.com/paper/1901.03003/) (2019)
- [Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution](https://mlsanity.com/paper/2112.08171/) (2021)
- [C3-STISR: Scene Text Image Super-resolution with Triple Clues](https://mlsanity.com/paper/2204.14044/) (2022)
- [Boosting Optical Character Recognition: A Super-Resolution Approach](https://mlsanity.com/paper/1506.02211/) (2015)
- [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)
- [Deep Laplacian Pyramid Network for Text Images Super-Resolution](https://mlsanity.com/paper/1811.10449/) (2018)
- [Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement](https://mlsanity.com/paper/2307.09749/) (2023)
- [Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2311.13317/) (2023)

## Built on by (most cited first, 1 of 1)

- [TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution](https://mlsanity.com/paper/2609.29240/) (2026)

## Abstract (arXiv)

Scene text image super-resolution (STISR) enhances the resolution and quality of low-resolution images. Unlike previous studies that treated scene text images as natural images, recent methods using a text prior (TP), extracted from a pre-trained text recognizer, have shown strong performance. However, two major issues emerge: (1) Explicit categorical priors, like TP, can negatively impact STISR if incorrect. We reveal that these explicit priors are unstable and propose replacing them with Non-CAtegorical Prior (NCAP) using penultimate layer representations. (2) Pre-trained recognizers used to generate TP struggle with low-resolution images. To address this, most studies jointly train the recognizer with the STISR network to bridge the domain gap between low- and high-resolution images, but this can cause an overconfidence phenomenon in the prior modality. We highlight this issue and propose a method to mitigate it by mixing hard and soft labels. Experiments on the TextZoom dataset demonstrate an improvement by 3.5%, while our method significantly enhances generalization performance by 14.8% across four text recognition datasets. Our method generalizes to all TP-guided STISR networks.