Systems and methods for three-dimensional pose determination

Mahdi Rad; Markus Oberweger; Vincent Lepetit

Systems and methods for three-dimensional pose determination

Mahdi Rad (Erfinder), Markus Oberweger (Erfinder), Vincent Lepetit (Erfinder)

Institut für Maschinelles Sehen und Darstellen (7100)

Publikation: Schutzrecht › Patent

Abstract

A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.

Originalsprache	englisch
Publikationsstatus	Veröffentlicht - 11 Juni 2020

Dieses zitieren

@misc{cd39ab61de6841bb85d19e567d751538,

title = "Systems and methods for three-dimensional pose determination",

abstract = "A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.",

author = "Mahdi Rad and Markus Oberweger and Vincent Lepetit",

year = "2020",

month = jun,

day = "11",

language = "English",

type = "Patent",

}

TY - PAT

T1 - Systems and methods for three-dimensional pose determination

AU - Rad, Mahdi

AU - Oberweger, Markus

AU - Lepetit, Vincent

PY - 2020/6/11

Y1 - 2020/6/11

N2 - A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.

AB - A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.

M3 - Patent

ER -