Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Bayesian Video Matting Using Learnt Image Priors Nicholas Apostoloff and Andrew Fitzgibbon
 

Summary: Bayesian Video Matting Using Learnt Image Priors
Nicholas Apostoloff and Andrew Fitzgibbon
Robotics Research Group
University of Oxford
Oxford, OX1 4AJ, UK
{nema, awf}@robots.ox.ac.uk
Abstract
Video matting, or layer extraction, is a classic inverse prob-
lem in computer vision that involves the extraction of fore-
ground objects, and the alpha mattes that describe their
opacity, from a set of images. Modern approaches that
work with natural backgrounds often require user-labelled
"trimaps" that segment each image into foreground, back-
ground and unknown regions. For long sequences, the pro-
duction of accurate trimaps can be time consuming. In con-
trast, another class of approach depends on automatic back-
ground extraction to automate the process, but existing tech-
niques do not make use of spatiotemporal consistency, and
cannot take account of operator hints such as trimaps.
This paper presents a method inspired by natural image

  

Source: Apostoloff, Nicholas - Department of Engineering Science, University of Oxford

 

Collections: Engineering; Computer Technologies and Information Sciences