Cycle-SfM: Joint self-supervised learning of depth and camera motion from monocular image sequences

Understanding 3D scene geometry is a fundamental research topic in computer vision, including various subproblems, such as depth prediction, visual odometry, optical flow, etc. With the advent of artificial intelligence methods like deep learning, many approaches have emerged to deal with such probl...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Chaos (Woodbury, N.Y.) N.Y.), 2019-12, Vol.29 (12), p.123102-123102
Hauptverfasser:	Sun, Qiyu, Tang, Yang, Zhao, Chaoqiang
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial intelligence Cameras Computer vision Cost function Forecasting Image reconstruction Machine learning Odometers Optical flow (image analysis) Optimization Self-supervised learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!