Sciweavers

11 search results - page 1 / 3
» Tracking Motion, Deformation, and Texture Using Conditionall...
Sort
View
PAMI
2010
238views more  PAMI 2010»
13 years 2 months ago
Tracking Motion, Deformation, and Texture Using Conditionally Gaussian Processes
—We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, ...
Tim K. Marks, John R. Hershey, Javier R. Movellan
NIPS
2004
13 years 6 months ago
Joint Tracking of Pose, Expression, and Texture using Conditionally Gaussian Filters
We present a generative model and stochastic filtering algorithm for simultaneous tracking of 3D position and orientation, non-rigid motion, object texture, and background texture...
Tim K. Marks, John R. Hershey, J. Cooper Roddey, J...
ICIP
2008
IEEE
14 years 6 months ago
Optical flow based tracking and retexturing of garments
In this paper, we present a method for tracking and retexturing of garments that exploits the entire image information using the optical flow constraint instead of working with di...
Anna Hilsmann, Peter Eisert
ICASSP
2011
IEEE
12 years 8 months ago
Rao-Blackwellized particle filter for Gaussian mixture models and application to visual tracking
One of the most important problems in visual tracking is how to incrementally update the appearance model because the appearance of a target object can be easily changed with time...
Jungho Kim, In-So Kweon
CVPR
2008
IEEE
13 years 11 months ago
A theoretical analysis of linear and multi-linear models of image appearance
Linear and multi-linear models of object shape/appearance (PCA, 3DMM, AAM/ASM, multilinear tensors) have been very popular in computer vision. In this paper, we analyze the validi...
Yilei Xu, Amit K. Roy Chowdhury