New view generation from a video sequence

Szu Sheng Chen; Hsueh-Ming Hang

doi:10.1109/ISCAS.1998.698763

New view generation from a video sequence

Szu Sheng Chen^*, Hsueh-Ming Hang

^*Corresponding author for this work

Department of Electronics Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

The problem of three-dimensional (3-D) scene representation and view generation is a new subject in video signal processing. Our goal is to construct a new scene at a different viewing position based on a sequence of captured images. The method proposed here does not make use of a solid 3-D model of physical objects. We decompose the image into layers based upon the motion maps derived from consecutive frames of an image sequence, and then synthesize a new view by recomposing the layers. In this process, accurate motion information estimation and consistent layer data aggregation are two critical steps. Some results using a real image sequence are shown at the end.

Original language	English
Article number	698763
Pages (from-to)	IV81 - IV84
Number of pages	4
Journal	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	4
DOIs	https://doi.org/10.1109/ISCAS.1998.698763
State	Published - 31 May 1998
Event	Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, ISCAS. Part 5 (of 6) - Monterey, CA, USA Duration: 31 May 1998 → 3 Jun 1998

Access to Document

10.1109/ISCAS.1998.698763

Fingerprint Dive into the research topics of 'New view generation from a video sequence'. Together they form a unique fingerprint.

Cite this

@article{62237897f87e4e9b8a09c4ad1f05f5b5,

title = "New view generation from a video sequence",

abstract = "The problem of three-dimensional (3-D) scene representation and view generation is a new subject in video signal processing. Our goal is to construct a new scene at a different viewing position based on a sequence of captured images. The method proposed here does not make use of a solid 3-D model of physical objects. We decompose the image into layers based upon the motion maps derived from consecutive frames of an image sequence, and then synthesize a new view by recomposing the layers. In this process, accurate motion information estimation and consistent layer data aggregation are two critical steps. Some results using a real image sequence are shown at the end.",

author = "Chen, {Szu Sheng} and Hsueh-Ming Hang",

year = "1998",

month = may,

day = "31",

doi = "10.1109/ISCAS.1998.698763",

language = "English",

volume = "4",

pages = "IV81 -- IV84",

journal = "Proceedings - IEEE International Symposium on Circuits and Systems",

issn = "0271-4310",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "null ; Conference date: 31-05-1998 Through 03-06-1998",

}

TY - JOUR

T1 - New view generation from a video sequence

AU - Chen, Szu Sheng

AU - Hang, Hsueh-Ming

PY - 1998/5/31

Y1 - 1998/5/31

N2 - The problem of three-dimensional (3-D) scene representation and view generation is a new subject in video signal processing. Our goal is to construct a new scene at a different viewing position based on a sequence of captured images. The method proposed here does not make use of a solid 3-D model of physical objects. We decompose the image into layers based upon the motion maps derived from consecutive frames of an image sequence, and then synthesize a new view by recomposing the layers. In this process, accurate motion information estimation and consistent layer data aggregation are two critical steps. Some results using a real image sequence are shown at the end.

AB - The problem of three-dimensional (3-D) scene representation and view generation is a new subject in video signal processing. Our goal is to construct a new scene at a different viewing position based on a sequence of captured images. The method proposed here does not make use of a solid 3-D model of physical objects. We decompose the image into layers based upon the motion maps derived from consecutive frames of an image sequence, and then synthesize a new view by recomposing the layers. In this process, accurate motion information estimation and consistent layer data aggregation are two critical steps. Some results using a real image sequence are shown at the end.

UR - http://www.scopus.com/inward/record.url?scp=0031645340&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.1998.698763

DO - 10.1109/ISCAS.1998.698763

M3 - Conference article

AN - SCOPUS:0031645340

VL - 4

SP - IV81 - IV84

JO - Proceedings - IEEE International Symposium on Circuits and Systems

JF - Proceedings - IEEE International Symposium on Circuits and Systems

SN - 0271-4310

M1 - 698763

Y2 - 31 May 1998 through 3 June 1998

ER -