Simultaneous localization and mapping for video coding

Dieter Schmalstieg; Phillip Grasmug; Gerhard Reitmayr

Simultaneous localization and mapping for video coding

Dieter Schmalstieg (Inventor), Phillip Grasmug (Inventor), Gerhard Reitmayr (Inventor)

Institute of Computer Graphics and Vision (7100)

Research output: Patent

Abstract

Video encoding and decoding techniques are described in which a predictive image s formed from texture mapping a composite image to a proxy geometry that provides an approximation of a three-dimensional structure of a current image or a previously encoded or decoded image. A residual between the predictive image and the current image is used to encode or decode the current image.

Original language	English
Publication status	Published - 19 Nov 2019

Cite this

@misc{5038579b8d084e979f2327469206da5e,

title = "Simultaneous localization and mapping for video coding",

abstract = "Video encoding and decoding techniques are described in which a predictive image s formed from texture mapping a composite image to a proxy geometry that provides an approximation of a three-dimensional structure of a current image or a previously encoded or decoded image. A residual between the predictive image and the current image is used to encode or decode the current image.",

author = "Dieter Schmalstieg and Phillip Grasmug and Gerhard Reitmayr",

year = "2019",

month = nov,

day = "19",

language = "English",

type = "Patent",

}

TY - PAT

T1 - Simultaneous localization and mapping for video coding

AU - Schmalstieg, Dieter

AU - Grasmug, Phillip

AU - Reitmayr, Gerhard

PY - 2019/11/19

Y1 - 2019/11/19

N2 - Video encoding and decoding techniques are described in which a predictive image s formed from texture mapping a composite image to a proxy geometry that provides an approximation of a three-dimensional structure of a current image or a previously encoded or decoded image. A residual between the predictive image and the current image is used to encode or decode the current image.

AB - Video encoding and decoding techniques are described in which a predictive image s formed from texture mapping a composite image to a proxy geometry that provides an approximation of a three-dimensional structure of a current image or a previously encoded or decoded image. A residual between the predictive image and the current image is used to encode or decode the current image.

M3 - Patent

ER -