Parallel attention recursive generalization transformer for image super-resolution

Abstract Transformer architectures have demonstrated remarkable performance in image super-resolution (SR). However, existing Transformer-based models generally suffer from insufficient local feature modeling, weak feature representation capabilities, and unreasonable loss function design, especiall...

Descripció completa

Dades bibliogràfiques

Autors principals:	Jing Wang, Yuanyuan Hao, Hongxing Bai, Lingyu Yan
Format:	Artigo
Idioma:	Inglês
Publicat:	Nature Portfolio 2025-03-01
Col·lecció:	Scientific Reports
Matèries:	Transformer Self-attention Super-resolution Loss function
Accés en línia:	https://doi.org/10.1038/s41598-025-92377-y
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!