Sciweavers

78 search results - page 2 / 16
» Better Foreground Segmentation Through Graph Cuts
Sort
View
3DPVT
2006
IEEE
203views Visualization» more  3DPVT 2006»
14 years 1 months ago
Graph Cut Based Multiple View Segmentation for 3D Reconstruction
In this paper we propose a novel framework for efficiently extracting foreground objects in so called shortbaseline image sequences. We apply the obtained segmentation to improve...
Mario Sormann, Christopher Zach, Konrad F. Karner
CVPR
2010
IEEE
14 years 3 months ago
Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images
We present a method to segment a collection of unlabeled images while exploiting automatically discovered appearance patterns shared between them. Given an unlabeled pool of multi...
Yong Jae Lee, Kristen Grauman
ICIP
2009
IEEE
14 years 8 months ago
Modified Grabcut For Unsupervised Object Segmentation
We propose a fully automated variation of the GrabCut technique for segmenting comparatively simple images with little variation in background colour and relatively high contrast ...
IJCV
2008
201views more  IJCV 2008»
13 years 7 months ago
Probabilistic Fusion of Stereo with Color and Contrast for Bi-Layer Segmentation
This paper describes two algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contr...
Vladimir Kolmogorov, Antonio Criminisi, Andrew Bla...
ICCV
2001
IEEE
14 years 9 months ago
Image Segmentation with Minimum Mean Cut
We introduce a new graph-theoretic approach to image segmentation based on minimizing a novel class of `mean cut' cost functions. Minimizing these cost functions corresponds ...
Song Wang, Jeffrey Mark Siskind