Sciweavers

400 search results - page 32 / 80
» Moving Proofs-As-Programs into Practice
Sort
View
CVPR
2008
IEEE
14 years 9 months ago
Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories
We examine the problem of segmenting tracked feature point trajectories of multiple moving objects in an image sequence. Using the affine camera model, this motion segmentation pr...
René Vidal, Roberto Tron, Shankar Rao, Yi M...
CVPR
2008
IEEE
14 years 9 months ago
Modeling complex luminance variations for target tracking
Lambert's model is widely used in low level computer vision algorithms such as matching, tracking or optical flow computation for example. However, it is well known that thes...
Éric Marchand, Christophe Collewet
ICCV
2007
IEEE
14 years 9 months ago
Evaluation of Large Scale Scene Reconstruction
We present an evaluation methodology and data for large scale video-based 3D reconstruction. We evaluate the effects of several parameters and draw conclusions that can be useful ...
Paul Merrell, Philippos Mordohai, Jan-Michael Frah...
ICCV
2001
IEEE
14 years 9 months ago
Do Ambiguous Reconstructions Always Give Ambiguous Images?
In many cases self-calibration is not able to yield a unique solution for the 3D reconstruction of a scene. This is due to the occurrence of critical motion sequences. If this is ...
Marc Pollefeys, Luc J. Van Gool
ECCV
2004
Springer
14 years 9 months ago
Weighted Minimal Hypersurfaces and Their Applications in Computer Vision
Abstract. Many interesting problems in computer vision can be formulated as a minimization problem for an energy functional. If this functional is given as an integral of a scalar-...
Bastian Goldlücke, Marcus A. Magnor