Sciweavers

CVPR
1997
IEEE
14 years 11 months ago
Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces
Shape indexing is a way of making rapid associations between features detected in an image and object models that could have produced them. When model databases are large, the use...
Jeffrey S. Beis, David G. Lowe
CVPR
1997
IEEE
14 years 11 months ago
Novel view synthesis in tensor space
We present a new method for synthesizing novel views of a 3D scene from few model images in full correspondence. The core of this work is the derivation of a tensorial operator th...
Shai Avidan, Amnon Shashua
CVPR
1997
IEEE
14 years 11 months ago
Pictorial Recognition Using Affine-Invariant Spectral Signatures
This paper describes an efficient approach to pose invariant object recognition employing pictorial recognition of image patches. A complete affine invariance is achieved by a rep...
Jezekiel Ben-Arie, Zhiqian Wang
CVPR
1996
IEEE
14 years 11 months ago
Video Browsing Using Edges and Motion
Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new m...
Ramin Zabih, Justin Miller, Kevin Mai
CVPR
1996
IEEE
14 years 11 months ago
Combination of Multiple Classifiers Using Local Accuracy Estimates
Kevin Woods, Kevin W. Bowyer, W. Philip Kegelmeyer
CVPR
1996
IEEE
14 years 11 months ago
Local Parallel Computation of Stochastic Completion Fields
Lance R. Williams, David W. Jacobs
CVPR
1996
IEEE
14 years 11 months ago
Minimal operator set for passive depth from defocus
A fundamental problem in depth from defocus is the measurement of relative defocus between images. We propose a class of broadband operators that, when used together, provide inva...
Masahiro Watanabe, Shree K. Nayar
CVPR
1996
IEEE
14 years 11 months ago
Determining Correspondences and Rigid Motion of 3-D Point Sets with Missing Data
This paper addresses the general 3-D rigid motion problem, where the point correspondences and the motion parameters between two sets of 3-D points are to be recovered. The existe...
Xiaoguang Wang, Yong-Qing Cheng, Robert T. Collins...
CVPR
1996
IEEE
14 years 11 months ago
A Framework for Recognizing a Facial Image from a Police Sketch
Robert G. Uhl Jr., Niels da Vitoria Lobo
CVPR
1996
IEEE
14 years 11 months ago
Comparison of Approaches to Egomotion Computation
We evaluated six algorithms for computing egomotion from image velocities. We established benchmarks for quantifying bias and sensitivity to noise, and for quantifying the converg...
Tina Yu Tian, Carlo Tomasi, David J. Heeger