TCSR: Lightweight Transformer and CNN Interaction Network for Image Super-Resolution

Convolutional neural network (CNN) has achieved impressive success in lightweight image super-resolution (SR) methods, yet the nature of its local operations constrains the SR performance. Recent Transformer has attracted increasing attention in lightweight SR methods owing to its remarkable global...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2024, Vol.12, p.174782-174795
Hauptverfasser:	Cai, Danlin, Tan, Wenwen, Chen, Feiyang, Lou, Xinchi, Xiahou, Jianbin, Zhu, Daxin, Huang, Detian
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Codecs Computational efficiency Computational modeling Computing costs convolutional neural network Convolutional neural networks Feature extraction Image quality Image reconstruction Image resolution Lightweight Lightweight image super-resolution Superresolution Training transformer Transformer cores Transformers UNet Weight reduction
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!