Sciweavers

1156 search results - page 200 / 232
» From 3D Shape Capture to Animated Models
Sort
View
NN
2002
Springer
161views Neural Networks» more  NN 2002»
13 years 7 months ago
AANN: an alternative to GMM for pattern recognition
The objective in any pattern recognition problem is to capture the characteristics common to each class from feature vectors of the training data. While Gaussian mixture models ap...
B. Yegnanarayana, S. P. Kishore
ICCV
2005
IEEE
14 years 1 months ago
On the Spatial Statistics of Optical Flow
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
Stefan Roth, Michael J. Black
ICRA
2006
IEEE
127views Robotics» more  ICRA 2006»
14 years 1 months ago
Controlling three Dimensional Swarms of Robots
— We address the problem of modeling and controlling a swarm of fully actuated point-like robots in three dimensions by generalizing the planar framework from [1]. We define a e...
Nathan Michael, Calin Belta, Vijay Kumar
CVPR
2008
IEEE
14 years 9 months ago
The Kneed Walker for human pose tracking
The Kneed Walker is a physics-based model derived from a planar biomechanical characterization of human locomotion. By controlling torques at the knees, hips and torso, the model ...
Marcus A. Brubaker, David J. Fleet
CVPR
2007
IEEE
14 years 9 months ago
A Surface-Growing Approach to Multi-View Stereo Reconstruction
We present a new approach to reconstruct the shape of a 3D object or scene from a set of calibrated images. The central idea of our method is to combine the topological flexibilit...
Martin Habbecke, Leif Kobbelt