Unsupervised Metric Relocalization Using Transform Consistency Loss

Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets. We instead propose a self-supervised solution, which exploit...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-11
Hauptverfasser:	Kasper, Mike, Nobre, Fernando, Heckman, Christoffer, Keivan, Nima
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Consistency
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!