Sciweavers

42 search results - page 2 / 9
» Computation of Highly Regular Nearby Points
Sort
View
PKDD
2009
Springer
153views Data Mining» more  PKDD 2009»
13 years 12 months ago
Subspace Regularization: A New Semi-supervised Learning Method
Most existing semi-supervised learning methods are based on the smoothness assumption that data points in the same high density region should have the same label. This assumption, ...
Yan-Ming Zhang, Xinwen Hou, Shiming Xiang, Cheng-L...
ICIP
2002
IEEE
14 years 7 months ago
Efficient selection of image patches with high motion confidence
Motion confidence measures aim to identify how well an image patch determines image motion. These kinds of confidence measures are commonly used to select points for optical flow ...
Peter Sand, Leonard McMillan
CVPR
2012
IEEE
11 years 7 months ago
Semantic structure from motion with points, regions, and objects
Structure from motion (SFM) aims at jointly recovering the structure of a scene as a collection of 3D points and estimating the camera poses from a number of input images. In this...
Sid Ying-Ze Bao, Mohit Bagra, Yu-Wei Chao, Silvio ...
COMPUTING
2004
204views more  COMPUTING 2004»
13 years 5 months ago
Image Registration by a Regularized Gradient Flow. A Streaming Implementation in DX9 Graphics Hardware
The presented image registration method uses a regularized gradient flow to correlate the intensities in two images. Thereby, an energy functional is successively minimized by des...
Robert Strzodka, Marc Droske, Martin Rumpf
CVPR
2005
IEEE
14 years 7 months ago
Correspondence Expansion for Wide Baseline Stereo
We present a new method for generating large numbers of accurate point correspondences between two wide baseline images. This is important for structure-from-motion algorithms, wh...
Kevin L. Steele, Parris K. Egbert