SynPo-Net—Accurate and Fast CNN-Based 6DoF Object Pose Estimation Using Synthetic Training

Estimation and tracking of 6DoF poses of objects in images is a challenging problem of great importance for robotic interaction and augmented reality. Recent approaches applying deep neural networks for pose estimation have shown encouraging results. However, most of them rely on training with real...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Yongzhi Su, Jason Rambach, Alain Pagani, Didier Stricker
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2021-01-01
Schriftenreihe:	Sensors
Schlagworte:	object pose estimation convolutional neural networks training with synthetic images deep learning domain adaptation 6DoF object pose
Online-Zugang:	https://www.mdpi.com/1424-8220/21/1/300
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!