Sciweavers

26 search results - page 2 / 6
» Faithful Shape Representation for 2D Gaussian Mixtures
Sort
View
ICCS
2007
Springer
13 years 11 months ago
Dynamic Tracking of Facial Expressions Using Adaptive, Overlapping Subspaces
We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear s...
Dimitris N. Metaxas, Atul Kanaujia, Zhiguo Li
ACCV
2006
Springer
13 years 11 months ago
Statistical Shape Models Using Elastic-String Representations
Abstract. To develop statistical models for shapes, we utilize an elastic string representation where curves (denoting shapes) can bend and locally stretch (or compress) to optimal...
Anuj Srivastava, Aastha Jain, Shantanu H. Joshi, D...
CVPR
2010
IEEE
14 years 1 months ago
Simultaneous Pose, Correspondence and Non-Rigid Shape
Recent works have shown that 3D shape of non-rigid surfaces can be accurately retrieved from a single image given a set of 3D-to-2D correspondences between that image and another ...
Jordi Sanchez, Jonas Ostlund, Pascal Fua, Francesc...
ICIP
2000
IEEE
13 years 10 months ago
Modelling Profiles with a Mixture of Gaussians
Point Distribution Models are useful tools for modelling the variability of particular classes of shapes. A common approach is to apply a Principle Component Analysis to the data,...
James Orwell, Darrel Greenhill, Jonathan D. Rymel,...
MICCAI
2007
Springer
14 years 6 months ago
Deformable Density Matching for 3D Non-rigid Registration of Shapes
There exists a large body of literature on shape matching and registration in medical image analysis. However, most of the previous work is focused on matching particular sets of f...
Arunabha S. Roy, Ajay Gopinath, Anand Rangarajan