Sciweavers

3005 search results - page 24 / 601
» Maximum-Likelihood Image Matching
Sort
View
73
Voted
CVPR
1999
IEEE
15 years 11 months ago
Implicit Representation and Scene Reconstruction from Probability Density Functions
A technique is presented for representing linear features as probability density functions in two or three dimensions. Three chief advantages of this approach are (1) a unified re...
Steven M. Seitz, P. Anandan
WSCG
2004
245views more  WSCG 2004»
14 years 11 months ago
Pel-Recursive Motion Estimation Using the Expectation-Maximization Technique and Spatial Adaptation
Pel-recursive motion estimation is a well-established approach. However, in the presence of noise, it becomes an ill-posed problem that requires regularization. In this paper, mot...
Vania V. Estrela, Luís A. Rivera, Marcos H....
AVSS
2005
IEEE
15 years 3 months ago
Multi-modal face image super-resolutions in tensor space
Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. To overcome these problems, super-resolution techniques...
Kui Jia, Shaogang Gong
CVPR
2008
IEEE
15 years 11 months ago
On errors-in-variables regression with arbitrary covariance and its application to optical flow estimation
Linear inverse problems in computer vision, including motion estimation, shape fitting and image reconstruction, give rise to parameter estimation problems with highly correlated ...
Björn Andres, Claudia Kondermann, Daniel Kond...
83
Voted
ICML
2008
IEEE
15 years 10 months ago
Efficiently learning linear-linear exponential family predictive representations of state
Exponential Family PSR (EFPSR) models capture stochastic dynamical systems by representing state as the parameters of an exponential family distribution over a shortterm window of...
David Wingate, Satinder P. Singh