Temporally coherent video matting

Sun Young Lee, Jong Chul Yoont, In Kwon Lee

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


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
Publication statusPublished - 2010
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


OtherACM SIGGRAPH 2010 Posters, SIGGRAPH '10
CountryUnited States
CityLos Angeles, CA

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Temporally coherent video matting'. Together they form a unique fingerprint.

  • 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