Defocus Video Matting

DSpace/Manakin Repository

Defocus Video Matting

Citable link to this page

. . . . . .

Title: Defocus Video Matting
Author: McGuire, Morgan; Matusik, Wojciech; Pfister, Hanspeter; Hughes, John F.; Durand, Frédo

Note: Order does not necessarily reflect citation order of authors.

Citation: McGuire, Morgan, Wojciech Matusik, Hanspeter Pfister, John F. Hughes, and Frédo Durand. 2005. Defocus video matting. In Proceedings International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2005 Papers: July 31 - August 04, 2005, Los Angeles, California, 567-576. New York, N.Y.: ACM Press. Also published in ACM Transactions on Graphics 24(3): 567-576. 5ACM SIGGRAPH 2005 Papers: 567-576.
Full Text & Related Files:
Abstract: Video matting is the process of pulling a high-quality alpha matte and foreground from a video sequence. Current techniques require either a known background (e.g., a blue screen) or extensive user interaction (e.g., to specify known foreground and background elements). The matting problem is generally under-constrained, since not enough information has been collected at capture time. We propose a novel, fully autonomous method for pulling a matte using multiple synchronized video streams that share a point of view but differ in their plane of focus. The solution is obtained by directly minimizing the error in filter-based image formation equations, which are over-constrained by our rich data stream. Our system solves the fully dynamic video matting problem without user assistance: both the foreground and background may be high frequency and have dynamic content, the foreground may resemble the background, and the scene is lit by natural (as opposed to polarized or collimated) illumination.
Published Version: doi:10.1145/1073204.1073231
Other Sources: http://gvi.seas.harvard.edu/sites/all/files/sig2005-matting_0.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAA
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:4101995

Show full Dublin Core record

This item appears in the following Collection(s)

  • FAS Scholarly Articles [7594]
    Peer reviewed scholarly articles from the Faculty of Arts and Sciences of Harvard University
 
 

Search DASH


Advanced Search
 
 

Submitters