Sciweavers

244 search results - page 1 / 49
» Generalized RANSAC Framework for Relaxed Correspondence Prob...
Sort
View
3DPVT
2006
IEEE
213views Visualization» more  3DPVT 2006»
13 years 11 months ago
Generalized RANSAC Framework for Relaxed Correspondence Problems
Finding correspondences between two (widely) separated views is essential for several computer vision tasks, such as structure and motion estimation and object recognition. In the...
Wei Zhang, Jana Kosecka
ICCV
2009
IEEE
14 years 10 months ago
GroupSAC: Efficient Consensus in the Presence of Groupings
We present a novel variant of the RANSAC algorithm that is much more efficient, in particular when dealing with problems with low inlier ratios. Our algorithm assumes that there...
Kai Ni, Hailin Jin, Frank Dellaert
PR
2000
130views more  PR 2000»
13 years 5 months ago
Self-annealing and self-annihilation: unifying deterministic annealing and relaxation labeling
Deterministic annealing and relaxation labeling algorithms for classification and matching are presented and discussed. A new approach--self annealing--is introduced to bring dete...
Anand Rangarajan
CVPR
1998
IEEE
14 years 7 months ago
A Statistical Framework for Long-Range Feature Matching in Uncalibrated Image Mosaicing
The problem considered in this paper is that of estimating the projective transformation between two images in situations where the image motion is large and featurematching is no...
Tat-Jen Cham, Roberto Cipolla
CORR
2007
Springer
130views Education» more  CORR 2007»
13 years 5 months ago
Lagrangian Relaxation for MAP Estimation in Graphical Models
Abstract— We develop a general framework for MAP estimation in discrete and Gaussian graphical models using Lagrangian relaxation techniques. The key idea is to reformulate an in...
Jason K. Johnson, Dmitry M. Malioutov, Alan S. Wil...