Temporally coherent video matting

Sun Young Lee, Jong Chul Yoont, In Kwon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationACM SIGGRAPH 2010 Posters, SIGGRAPH '10
DOIs
Publication statusPublished - 2010 Sep 7
EventACM SIGGRAPH 2010 Posters, SIGGRAPH '10 - Los Angeles, CA, United States
Duration: 2010 Jul 262010 Jul 30

Publication series

NameACM SIGGRAPH 2010 Posters, SIGGRAPH '10

Other

OtherACM SIGGRAPH 2010 Posters, SIGGRAPH '10
CountryUnited States
CityLos Angeles, CA
Period10/7/2610/7/30

Fingerprint

Flickering

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Lee, S. Y., Yoont, J. C., & Lee, I. K. (2010). Temporally coherent video matting. In ACM SIGGRAPH 2010 Posters, SIGGRAPH '10 [77] (ACM SIGGRAPH 2010 Posters, SIGGRAPH '10). https://doi.org/10.1145/1836845.1836928
Lee, Sun Young ; Yoont, Jong Chul ; Lee, In Kwon. / Temporally coherent video matting. ACM SIGGRAPH 2010 Posters, SIGGRAPH '10. 2010. (ACM SIGGRAPH 2010 Posters, SIGGRAPH '10).
@inproceedings{3ceff787b9ba48e38a741bbe72f2d6c5,
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.",
author = "Lee, {Sun Young} and Yoont, {Jong Chul} and Lee, {In Kwon}",
year = "2010",
month = "9",
day = "7",
doi = "10.1145/1836845.1836928",
language = "English",
isbn = "9781450303934",
series = "ACM SIGGRAPH 2010 Posters, SIGGRAPH '10",
booktitle = "ACM SIGGRAPH 2010 Posters, SIGGRAPH '10",

}

Lee, SY, Yoont, JC & Lee, IK 2010, Temporally coherent video matting. in ACM SIGGRAPH 2010 Posters, SIGGRAPH '10., 77, ACM SIGGRAPH 2010 Posters, SIGGRAPH '10, ACM SIGGRAPH 2010 Posters, SIGGRAPH '10, Los Angeles, CA, United States, 10/7/26. https://doi.org/10.1145/1836845.1836928

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

ACM SIGGRAPH 2010 Posters, SIGGRAPH '10. 2010. 77 (ACM SIGGRAPH 2010 Posters, SIGGRAPH '10).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Temporally coherent video matting

AU - Lee, Sun Young

AU - Yoont, Jong Chul

AU - Lee, In Kwon

PY - 2010/9/7

Y1 - 2010/9/7

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.

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.

UR - http://www.scopus.com/inward/record.url?scp=77956220460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956220460&partnerID=8YFLogxK

U2 - 10.1145/1836845.1836928

DO - 10.1145/1836845.1836928

M3 - Conference contribution

AN - SCOPUS:77956220460

SN - 9781450303934

T3 - ACM SIGGRAPH 2010 Posters, SIGGRAPH '10

BT - ACM SIGGRAPH 2010 Posters, SIGGRAPH '10

ER -

Lee SY, Yoont JC, Lee IK. Temporally coherent video matting. In ACM SIGGRAPH 2010 Posters, SIGGRAPH '10. 2010. 77. (ACM SIGGRAPH 2010 Posters, SIGGRAPH '10). https://doi.org/10.1145/1836845.1836928