Sciweavers

CVPR
2001
IEEE
14 years 12 months ago
Generic Model Abstraction from Examples
Model Abstraction from Examples Yakov Keselman, Member, IEEE, and Sven Dickinson, Member, IEEE The recognition community has typically avoided bridging the representational gap bet...
Yakov Keselman, Sven J. Dickinson
CVPR
2001
IEEE
14 years 12 months ago
Handling Occlusions in Dense Multi-view Stereo
While stereo matching was originally formulated as the recovery of 3D shape from a pair of images, it is now generally recognized that using more than two images can dramatically ...
Sing Bing Kang, Richard Szeliski, Jinxiang Chai
CVPR
2001
IEEE
14 years 12 months ago
Critical Configurations for N-view Projective Reconstruction
In this paper we give a complete characterization of critical configurations for projective reconstruction with any number of points and views. A set of cameras and points is said...
Fredrik Kahl, Kalle Åström, Richard I. ...
CVPR
2001
IEEE
14 years 12 months ago
Finding Folds: On the Appearance and Identification of Occlusion
Patrick S. Huggins, Hansen F. Chen, Peter N. Belhu...
CVPR
2001
IEEE
14 years 12 months ago
Learning Flexible Sprites in Video Layers
See a PPT file with videos at www.research.microsoft.com/users/jojic/FlexiblesSprites.htm We propose a technique for automatically learning layers of "flexible sprites" ...
Nebojsa Jojic, Brendan J. Frey
CVPR
2001
IEEE
14 years 12 months ago
Robust Online Appearance Models for Visual Tracking
Allan D. Jepson, David J. Fleet, Thomas F. El-Mara...
CVPR
2001
IEEE
14 years 12 months ago
Alpha Channel Estimation in High Resolution Images and Image Sequences
For Motion Picture Special Effects, it is often necessary to take a source image of an actor, segment the actor from the unwanted background, and then composite over a new backgro...
P. Hillman, John M. Hannah, David S. Renshaw
CVPR
2001
IEEE
14 years 12 months ago
Geometric Distributions for Catadioptric Sensor Design
We present a general method of catadioptric sensor design for realizing prescribed projections. Our method makes use of geometric distributions in 3-dimensional space, which are g...
R. Andrew Hicks, Ronald K. Perline
CVPR
2001
IEEE
14 years 12 months ago
Mixtures of Trees for Object Recognition
Efficient detection of objects in images is complicated by variations of object appearance due to intra-class object differences, articulation, lighting, occlusions, and aspect va...
Sergey Ioffe, David A. Forsyth