SELF-SUPERVISED MONOCULAR DEPTH ESTIMATION VIA RIGID-MOTION EMBEDDINGS

SELF-SUPERVISED MONOCULAR DEPTH ESTIMATION VIA RIGID-MOTION EMBEDDINGS

System, methods, and other embodiments described herein relate to training a depth model for monocular depth estimation using photometric loss masks derived from motion estimates of dynamic objects. In one embodiment, a method includes generating depth maps from images of an environment. The method...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zakharov, Sergey, Guizilini, Vitor, Ambrus, Rares A, Gaidon, Adrien David
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:System, methods, and other embodiments described herein relate to training a depth model for monocular depth estimation using photometric loss masks derived from motion estimates of dynamic objects. In one embodiment, a method includes generating depth maps from images of an environment. The method includes determining motion of points within the depth maps. The method includes associating the points between the depth maps to identify an object according to a correlation of the motion for a first cluster of the points with a second cluster of the points. The method includes providing the depth maps and the object as an electronic output.