Estimation of 6D Pose of Objects Based on a Variant Adversarial Autoencoder

The goal of this paper is to estimate object’s 6D pose based on the texture-less dataset. The pose of each projection view is obtained by rendering the 3D model of each object, and then the orientation feature of the object is implicitly represented by the latent space obtained from the RGB image. T...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural processing letters 2023-12, Vol.55 (7), p.9581-9596
Hauptverfasser:	Huang, Dan, Ahn, Hyemin, Li, Shile, Hu, Yueming, Lee, Dongheui
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations Artificial Intelligence Coders Color imagery Complex Systems Computational Intelligence Computer Science Datasets Feature extraction Methods Normal distribution Pose estimation Template matching Three dimensional models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!