Temporally coherent video matting

Sun Young Lee, Jong Chul Yoon, In Kwon Lee

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Existing video matting approaches determine the alpha matte sequence frame-by-frame, which lead to flickering near the boundary of the foreground region. We reduce this effect by considering video data as a spatio-temporal cube, and extending a robust matting algorithm to a 3D solver. Our results demonstrate consistent and visually pleasing alpha mattes, and tend to preserve temporal coherence better than previous techniques. Crown

Original languageEnglish
Pages (from-to)25-33
Number of pages9
JournalGraphical Models
Volume72
Issue number3
DOIs
Publication statusPublished - 2010 May 1

Fingerprint

Flickering
Robust Algorithm
Regular hexahedron
Tend
Demonstrate

All Science Journal Classification (ASJC) codes

  • Software
  • Modelling and Simulation
  • Geometry and Topology
  • Computer Graphics and Computer-Aided Design

Cite this

Lee, Sun Young ; Yoon, Jong Chul ; Lee, In Kwon. / Temporally coherent video matting. In: Graphical Models. 2010 ; Vol. 72, No. 3. pp. 25-33.
@article{cb44ff6bceaa42a88db0fa201175f5d4,
title = "Temporally coherent video matting",
abstract = "Existing video matting approaches determine the alpha matte sequence frame-by-frame, which lead to flickering near the boundary of the foreground region. We reduce this effect by considering video data as a spatio-temporal cube, and extending a robust matting algorithm to a 3D solver. Our results demonstrate consistent and visually pleasing alpha mattes, and tend to preserve temporal coherence better than previous techniques. Crown",
author = "Lee, {Sun Young} and Yoon, {Jong Chul} and Lee, {In Kwon}",
year = "2010",
month = "5",
day = "1",
doi = "10.1016/j.gmod.2010.03.001",
language = "English",
volume = "72",
pages = "25--33",
journal = "Graphical Models",
issn = "1524-0703",
publisher = "Elsevier Inc.",
number = "3",

}

Temporally coherent video matting. / Lee, Sun Young; Yoon, Jong Chul; Lee, In Kwon.

In: Graphical Models, Vol. 72, No. 3, 01.05.2010, p. 25-33.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Temporally coherent video matting

AU - Lee, Sun Young

AU - Yoon, Jong Chul

AU - Lee, In Kwon

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Existing video matting approaches determine the alpha matte sequence frame-by-frame, which lead to flickering near the boundary of the foreground region. We reduce this effect by considering video data as a spatio-temporal cube, and extending a robust matting algorithm to a 3D solver. Our results demonstrate consistent and visually pleasing alpha mattes, and tend to preserve temporal coherence better than previous techniques. Crown

AB - Existing video matting approaches determine the alpha matte sequence frame-by-frame, which lead to flickering near the boundary of the foreground region. We reduce this effect by considering video data as a spatio-temporal cube, and extending a robust matting algorithm to a 3D solver. Our results demonstrate consistent and visually pleasing alpha mattes, and tend to preserve temporal coherence better than previous techniques. Crown

UR - http://www.scopus.com/inward/record.url?scp=77950565878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950565878&partnerID=8YFLogxK

U2 - 10.1016/j.gmod.2010.03.001

DO - 10.1016/j.gmod.2010.03.001

M3 - Article

AN - SCOPUS:77950565878

VL - 72

SP - 25

EP - 33

JO - Graphical Models

JF - Graphical Models

SN - 1524-0703

IS - 3

ER -