Pose estimation and model retrieval for objects in images

Alexander Grabner (Inventor), Peter M. Roth (Inventor), Vincent Lepetit (Inventor)

Research output: PatentResearch

Abstract

Techniques are provided for selecting a three-dimensional model. An input image including an object can be obtained, and a pose of the object in the input image can be determined. One or more candidate three-dimensional models representing one or more objects in the determined pose can be obtained. From the one or more candidate three-dimensional models, a candidate three-dimensional model can be determined to represent the object in the input image.
Original languageEnglish
Publication statusPublished - 2019

Cite this

@misc{ad1111e3c81b4867a818a6308085986c,
title = "Pose estimation and model retrieval for objects in images",
abstract = "Techniques are provided for selecting a three-dimensional model. An input image including an object can be obtained, and a pose of the object in the input image can be determined. One or more candidate three-dimensional models representing one or more objects in the determined pose can be obtained. From the one or more candidate three-dimensional models, a candidate three-dimensional model can be determined to represent the object in the input image.",
author = "Alexander Grabner and Roth, {Peter M.} and Vincent Lepetit",
year = "2019",
language = "English",
type = "Patent",

}

TY - PAT

T1 - Pose estimation and model retrieval for objects in images

AU - Grabner, Alexander

AU - Roth, Peter M.

AU - Lepetit, Vincent

PY - 2019

Y1 - 2019

N2 - Techniques are provided for selecting a three-dimensional model. An input image including an object can be obtained, and a pose of the object in the input image can be determined. One or more candidate three-dimensional models representing one or more objects in the determined pose can be obtained. From the one or more candidate three-dimensional models, a candidate three-dimensional model can be determined to represent the object in the input image.

AB - Techniques are provided for selecting a three-dimensional model. An input image including an object can be obtained, and a pose of the object in the input image can be determined. One or more candidate three-dimensional models representing one or more objects in the determined pose can be obtained. From the one or more candidate three-dimensional models, a candidate three-dimensional model can be determined to represent the object in the input image.

M3 - Patent

ER -