An improved recurrent neural networks for 3d object reconstruction

3D-R2N2 and other advanced 3D reconstruction neural networks have achieved impressive results, however most of them still suffer from training difficulties and detail losing, due to their weak feature extraction capability and improper loss function. This paper aims to overcome these shortcomings an...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied intelligence (Dordrecht, Netherlands) Netherlands), 2020-03, Vol.50 (3), p.905-923
Hauptverfasser:	Ma, Tingsong, Kuang, Ping, Tian, Wenhong
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Chamfering Coders Computer Science Feature extraction Machines Manufacturing Mechanical Engineering Neural networks Processes Reconstruction Recurrent neural networks Three dimensional models Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!