GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization

Direct SLAM methods have shown exceptional performance on odometry tasks. However, they are susceptible to dynamic lighting and weather changes while also suffering from a bad initialization on large baselines. To overcome this, we propose GN-Net: a network optimized with the novel Gauss-Newton loss...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE robotics and automation letters 2020-04, Vol.5 (2), p.890-897
Hauptverfasser:	von Stumberg, Lukas, Wenzel, Patrick, Khan, Qadeer, Cremers, Daniel
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmark testing Benchmarks Lighting Localization Meteorology Odometers Simultaneous localization and mapping SLAM Task analysis Training visual learning Visualization Weather
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!