Sciweavers

190 search results - page 33 / 38
» Shape Estimation in Natural Illumination
Sort
View
CVPR
2003
IEEE
14 years 10 months ago
Object Class Recognition by Unsupervised Scale-Invariant Learning
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constel...
Robert Fergus, Pietro Perona, Andrew Zisserman
CVPR
2008
IEEE
1094views Computer Vision» more  CVPR 2008»
14 years 10 months ago
Image super-resolution using gradient profile prior
In this paper, we propose an image super-resolution approach using a novel generic image prior ? gradient profile prior, which is a parametric prior describing the shape and the s...
Jian Sun, Zongben Xu, Heung-Yeung Shum
ICIP
1999
IEEE
14 years 9 months ago
Uncertainties in Bayesian Geometric Models
Deformable geometric models fit very naturally into the context of Bayesian analysis. The prior probability of boundary shapes is taken to proportional to the negative exponential...
Kenneth M. Hanson, Gregory S. Cunningham, Robert J...
ICMCS
2005
IEEE
201views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Head Tracking Using Particle Filter with Intensity Gradient and Color Histogram
This paper presents a method for tracking human head using a particle filter to naturally integrate two complementary cues: intensity gradient and color histogram. The shape of th...
Xinyu Xu, Baoxin Li
BMVC
2000
13 years 9 months ago
3D Model Acquisition by Tracking 2D Wireframes
This paper presents a semi-automatic wireframe acquisition system. The system uses real-time (25Hz) tracking of a user specified 2D wireframe and intermittent camera pose paramete...
M. Brown, Tom Drummond, Roberto Cipolla