SHAPE CONSTRUCTION-BASED MACHINE LEARNING MODEL FOR OBJECT LOCALIZATION

SHAPE CONSTRUCTION-BASED MACHINE LEARNING MODEL FOR OBJECT LOCALIZATION

Methods and systems for training a model include performing two-dimensional object detection on a training image to identify an object. The training image is cropped around the object. A category-level shape reconstruction is generated using a neural radiance field model. A normalized coordinate mod...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Buyu, Schulter, Samuel, Min, Zhixiang, Zhuang, Bingbing
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
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:Methods and systems for training a model include performing two-dimensional object detection on a training image to identify an object. The training image is cropped around the object. A category-level shape reconstruction is generated using a neural radiance field model. A normalized coordinate model is trained using the training image and ground truth information from the category-level shape reconstruction.