Sciweavers

93 search results - page 14 / 19
» Probabilistic human pose recovery from 2D images
Sort
View
ICIP
2004
IEEE
14 years 9 months ago
Complete 3-d models from video: a global approach
We address the automatic recovery of complete 3-D object models from video streams. Usually, complete 3-D models are built by fusing several depth maps, each computed from a small...
Bruno B. Gonçalves, Pedro M. Q. Aguiar
CVPR
2006
IEEE
14 years 1 months ago
Depth from Familiar Objects: A Hierarchical Model for 3D Scenes
We develop an integrated, probabilistic model for the appearance and three-dimensional geometry of cluttered scenes. Object categories are modeled via distributions over the 3D lo...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
PAMI
2006
221views more  PAMI 2006»
13 years 7 months ago
Face Recognition from a Single Training Image under Arbitrary Unknown Lighting Using Spherical Harmonics
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one t...
Lei Zhang 0002, Dimitris Samaras
CVPR
2006
IEEE
14 years 9 months ago
Robust AAM Fitting by Fusion of Images and Disparity Data
Active Appearance Models (AAMs) have been popularly used to represent the appearance and shape variations of human faces. Fitting an AAM to images recovers the face pose as well a...
Joerg Liebelt, Jing Xiao, Jie Yang
DAGM
2007
Springer
14 years 1 months ago
Online Smoothing for Markerless Motion Capture
Tracking 3D objects from 2D image data often leads to jittery tracking results. In general, unsmooth motion is a sign of tracking errors, which, in the worst case, can cause the tr...
Bodo Rosenhahn, Thomas Brox, Daniel Cremers, Hans-...