Sciweavers

84 search results - page 1 / 17
» Observable Subspaces for 3D Human Motion Recovery
Sort
View
CVPR
2009
IEEE
1132views Computer Vision» more  CVPR 2009»
15 years 2 months ago
Observable Subspaces for 3D Human Motion Recovery
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. T...
Andrea Fossati (EPFL), Mathieu Salzmann (Universit...
CVPR
2009
IEEE
15 years 2 months ago
Multi-view 3D Human Pose Estimation combining Single-frame Recovery, Temporal Integration and Model Adaptation
We present a system for the estimation of unconstrained 3D human upper body movement from multiple cameras. Its main novelty lies in the integration of three components: single-...
Dariu M. Gavrila, Michael Hofmann
3DPVT
2004
IEEE
169views Visualization» more  3DPVT 2004»
13 years 10 months ago
View Dependence of 3D Recovery from Folded Pictures and Warped 3D Faces
In a popular visual illusion, the portrait on paper currency is folded into an M shape along vertical lines through the nose and the eyes. When this folded picture is tilted back ...
J. Patrick Cavanagh, Michael von Grünau, Lee ...
ICCV
1999
IEEE
13 years 11 months ago
Multi-Frame Optical Flow Estimation using Subspace Constraints
We show that the set of all ow- elds in a sequence of frames imaging a rigid scene resides in a lowdimensional linear subspace. Based on this observation, we develop a method for ...
Michal Irani
ICIP
2004
IEEE
14 years 8 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