Sciweavers

CVPR
1996
IEEE
13 years 8 months ago
A Space-Sweep Approach to True Multi-Image Matching
The problem of determining feature correspondences across multiple views is considered. The term true multi-image" matching is introduced to describe techniques that make ful...
Robert T. Collins
ECCV
2000
Springer
13 years 9 months ago
Factorization with Uncertainty
Factorization using Singular Value Decomposition (SVD) is often used for recovering 3D shape and motion from feature correspondences across multiple views. SVD is powerful at find...
Michal Irani, P. Anandan
SI3D
2003
ACM
13 years 9 months ago
Interactive image-based rendering using feature globalization
Image-based rendering (IBR) systems enable virtual walkthroughs of photorealistic environments by warping and combining reference images to novel viewpoints under interactive user...
Daniel G. Aliaga, Dimah Yanovsky, Thomas A. Funkho...
ICPR
2008
IEEE
13 years 11 months ago
Structure from Motion: Combining features correspondences and optical flow
This paper suggests using discrete feature displacements and optical flow simultaneously to determine the camera motion and its velocity. This is advantageous when the number of ...
Adel H. Fakih, John Zelek
ICPR
2008
IEEE
13 years 11 months ago
Robust relative pose estimation with integrated cheirality constraint
The cheirality constraint, which requires that reconstructed point correspondences lie in front of the cameras, has not typically been integrated into traditional RANSAC-based pos...
Wei Xu, Jane Mulligan
CVPR
2007
IEEE
14 years 6 months ago
Image Matching via Saliency Region Correspondences
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
Alexander Toshev, Jianbo Shi, Kostas Daniilidis
CVPR
2006
IEEE
14 years 6 months ago
Unsupervised Learning of Categories from Sets of Partially Matching Image Features
We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
Kristen Grauman, Trevor Darrell
CVPR
1998
IEEE
14 years 6 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