EDFIDepth: enriched multi-path vision transformer feature interaction networks for monocular depth estimation

Monocular depth estimation (MDE) aims to predict pixel-level dense depth maps from a single RGB image. Some recent approaches mainly rely on encoder–decoder architectures to capture and process multi-scale features. However, they usually exploit heavier network at the expense of computational costs...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	The Journal of supercomputing 2024-09, Vol.80 (14), p.21023-21047
Hauptverfasser:	Xia, Chenxing, Zhang, Mengge, Gao, Xiuju, Ge, Bin, Li, Kuan-Ching, Fang, Xianjin, Zhang, Yan, Liang, Xingzhu
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Coders Compilers Computer Science Computing costs Datasets Interpreters Lightweight Modules Parameters Processor Architectures Programming Languages Weight reduction
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!