# Deep Laplacian Pyramid Network for Text Images Super-Resolution

arXiv: https://arxiv.org/abs/1811.10449 · HTML: https://mlsanity.com/paper/1811.10449/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Text Prior Guided Scene Text Image Super-resolution](https://mlsanity.com/paper/2106.15368/) (2021)
- [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)
- [Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution](https://mlsanity.com/paper/2309.08919/) (2023)
- [One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer](https://mlsanity.com/paper/2308.02770/) (2023)
- [SDT-DCSCN for Simultaneous Super-Resolution and Deblurring of Text Images](https://mlsanity.com/paper/2201.05865/) (2022)
- [Efficient scene text image super-resolution with semantic guidance](https://mlsanity.com/paper/2403.13330/) (2024)
- [NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior](https://mlsanity.com/paper/2504.00410/) (2025)

## Abstract (arXiv)

Convolutional neural networks have recently demonstrated interesting results for single image super-resolution. However, these networks were trained to deal with super-resolution problem on natural images. In this paper, we adapt a deep network, which was proposed for natural images superresolution, to single text image super-resolution. To evaluate the network, we present our database for single text image super-resolution. Moreover, we propose to combine Gradient Difference Loss (GDL) with L1/L2 loss to enhance edges in super-resolution image. Quantitative and qualitative evaluations on our dataset show that adding the GDL improves the super-resolution results.