A lightweight hybrid perception enhancement network for infrared image super-resolution

Abstract Infrared image super-resolution (SR) remains a challenging task due to inherent limitations in existing approaches: convolutional neural network (CNN)-based approaches struggle with long-range dependency modeling, whereas transformer-based approaches are computationally expensive and tend t...

Descrición completa

Detalles Bibliográficos

Principais autores:	Zepeng Liu, Jiya Tian, Chao Liu, Guodong Zhang
Formato:	Artigo
Idioma:	Inglês
Publicado:	Nature Portfolio 2026-01-01
Series:	Scientific Reports
Assuntos:	Infrared image super-resolution Hybrid perception Token aggregation Multi-scale
Acceso en liña:	https://doi.org/10.1038/s41598-026-37763-w
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!