RAFT-MSF: Self-Supervised Monocular Scene Flow Using Recurrent Optimizer

A popular approach to estimate scene flow is to utilize point cloud data from various Lidar scans. However, there is little attention to learning 3D motion from camera images. Learning scene flow from a monocular camera remains a challenging task due to its ill-posedness as well as lack of annotated...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	International journal of computer vision 2023-11, Vol.131 (11), p.2757-2769
Hauptverfasser:	Bayramli, Bayram, Hur, Junhwa, Lu, Hongtao
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Artificial Intelligence Cameras Computer Imaging Computer Science Image Processing and Computer Vision Learning Optical flow (image analysis) Optical radar Pattern Recognition Pattern Recognition and Graphics Remote sensing State of the art Three dimensional motion Vision
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!