Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 6040-6049 We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Remelli, Edoardo, Han, Shangchen, Honari, Sina, Fua, Pascal, Wang, Robert
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!