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...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Jing Wang, Yuanyuan Hao, Hongxing Bai, Lingyu Yan
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	Nature Portfolio 2025-03-01
Serie:	Scientific Reports
Soggetti:	Transformer Self-attention Super-resolution Loss function
Accesso online:	https://doi.org/10.1038/s41598-025-92377-y
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!