Feb 21, 2023 · Abstract:Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, ...

We propose a novel Dual Prior Modulation Network. (DPMN), which leverages the text mask and the graphi- cal recognition result as priors, to improve the quality ...

Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will ...

It is necessary for you to modify the ./config/super_resolution.yaml file according to your path of dataset and recognizers. If you use 3 VisionLANs to generate ...

A plug-and-play module dubbed Dual Prior Modulation Network (DPMN), which leverages dual image-level priors to bring performance gain over existing approaches.

Oct 29, 2023 · Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, ...

On-demand video platform giving you access to lectures from conferences worldwide.

A comprehensive repository of awesome Scene Text Image Super-Resolution (STISR) methods based on deep learning.

This paper makes an inspiring attempt to embed text recognition prior into STISR model, and adopts the predicted character recognition probability sequence ...

Scene text image super-resolution (STISR) aims to improve the resolution and visual quality of low-resolution (LR) scene text images, while simultaneously ...