RoHM: Robust Human Motion Reconstruction via Diffusion

We propose RoHM, an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos in the presence of noise and occlusions. Most previous approaches either train neural networks to directly regress motion in 3D or learn data-driven motion priors and combine them with optimization a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Zhang, Siwei, Bhatnagar, Bharat Lal, Xu, Yuanlu, Winkler, Alexander, Kadlecek, Petr, Tang, Siyu, Bogo, Federica
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!