Better Skeleton Better Readability: Scene Text Image Super-Resolution via Skeleton-Aware Diffusion Model

Scene text image super-resolution (STISR) aims to enhance the resolution of text images while simultaneously improving their readability by reducing noise, blur, and other degradations. Existing diffusion-based approaches for STISR primarily rely on text-prior information but often overlook the impo...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Shrey Singh, Prateek Keserwani, Partha Pratim Roy, Rajkumar Saini
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2024-01-01
Saila:	IEEE Access
Gaiak:	Scene text image super-resolution diffusion model skeleton networks text recognition
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/10772209/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!