Model retrieval for objects in images using field descriptors

Alexander Grabner; Peter M. Roth; Vincent Lepetit

Model retrieval for objects in images using field descriptors

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

Institute of Computer Graphics and Vision (7100)

Research output: Patent

Abstract

Techniques are provided for one or more three-dimensional models representing one or more objects. For example, an input image including one or more objects can be obtained. From the input image, a location field can be generated for each object of the one or more objects. A location field descriptor can be determined for each object of the one or more objects, and a location field descriptor for an object of the one or more objects can be compared to a plurality of location field descriptors for a plurality of three-dimensional models. A three-dimensional model can be selected from the plurality of three-dimensional models for each object of the one or more objects. A three-dimensional model can be selected for the object based on comparing a location field descriptor for the object to the plurality of location field descriptors for the plurality of three-dimensional models.

Original language	German
Publication status	Published - 10 Dec 2020

Cite this

@misc{d049ad4cb71b4cc9a84a7ae16bd1a242,

title = "Model retrieval for objects in images using field descriptors",

abstract = "Techniques are provided for one or more three-dimensional models representing one or more objects. For example, an input image including one or more objects can be obtained. From the input image, a location field can be generated for each object of the one or more objects. A location field descriptor can be determined for each object of the one or more objects, and a location field descriptor for an object of the one or more objects can be compared to a plurality of location field descriptors for a plurality of three-dimensional models. A three-dimensional model can be selected from the plurality of three-dimensional models for each object of the one or more objects. A three-dimensional model can be selected for the object based on comparing a location field descriptor for the object to the plurality of location field descriptors for the plurality of three-dimensional models.",

author = "Alexander Grabner and Roth, {Peter M.} and Vincent Lepetit",

year = "2020",

month = dec,

day = "10",

language = "deutsch",

type = "Patent",

}

TY - PAT

T1 - Model retrieval for objects in images using field descriptors

AU - Grabner, Alexander

AU - Roth, Peter M.

AU - Lepetit, Vincent

PY - 2020/12/10

Y1 - 2020/12/10

N2 - Techniques are provided for one or more three-dimensional models representing one or more objects. For example, an input image including one or more objects can be obtained. From the input image, a location field can be generated for each object of the one or more objects. A location field descriptor can be determined for each object of the one or more objects, and a location field descriptor for an object of the one or more objects can be compared to a plurality of location field descriptors for a plurality of three-dimensional models. A three-dimensional model can be selected from the plurality of three-dimensional models for each object of the one or more objects. A three-dimensional model can be selected for the object based on comparing a location field descriptor for the object to the plurality of location field descriptors for the plurality of three-dimensional models.

AB - Techniques are provided for one or more three-dimensional models representing one or more objects. For example, an input image including one or more objects can be obtained. From the input image, a location field can be generated for each object of the one or more objects. A location field descriptor can be determined for each object of the one or more objects, and a location field descriptor for an object of the one or more objects can be compared to a plurality of location field descriptors for a plurality of three-dimensional models. A three-dimensional model can be selected from the plurality of three-dimensional models for each object of the one or more objects. A three-dimensional model can be selected for the object based on comparing a location field descriptor for the object to the plurality of location field descriptors for the plurality of three-dimensional models.

M3 - Patent

ER -