Sciweavers

CVPR
2005
IEEE
14 years 7 months ago
Coherent Regions for Concise and Stable Image Description
We present a new method for summarizing images for the purposes of matching and registration. We take the point of view that large, coherent regions in the image provide a concise...
Jason J. Corso, Gregory D. Hager
CVPR
2005
IEEE
14 years 7 months ago
Two-View Geometry Estimation Unaffected by a Dominant Plane
Jiri Matas, Ondrej Chum, Tomás Werner
CVPR
2005
IEEE
14 years 7 months ago
A Rational Function Lens Distortion Model for General Cameras
We introduce a new rational function (RF) model for radial lens distortion in wide-angle and catadioptric lenses, which allows the simultaneous linear estimation of motion and len...
David Claus, Andrew W. Fitzgibbon
CVPR
2005
IEEE
14 years 7 months ago
Matching with PROSAC - Progressive Sample Consensus
A new robust matching method is proposed. The Progressive Sample Consensus (PROSAC) algorithm exploits the linear ordering defined on the set of correspondences by a similarity fu...
Ondrej Chum, Jiri Matas
CVPR
2005
IEEE
14 years 7 months ago
On Modelling Nonlinear Shape-and-Texture Appearance Manifolds
Statistical shape-and-texture appearance models employ image metamorphosis to form a rich, compact representation of object appearance. They achieve their efficiency by decomposin...
Chris Mario Christoudias, Trevor Darrell
CVPR
2005
IEEE
14 years 7 months ago
Learning a Similarity Metric Discriminatively, with Application to Face Verification
We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large an...
Sumit Chopra, Raia Hadsell, Yann LeCun
CVPR
2005
IEEE
14 years 7 months ago
Video Epitomes
Recently, "epitomes" were introduced as patch-based probability models that are learned by compiling together a large number of examples of patches from input images. In...
Vincent Cheung, Brendan J. Frey, Nebojsa Jojic
CVPR
2005
IEEE
14 years 7 months ago
MER-DIMES: A Planetary Landing Application of Computer Vision
During the Mars Exploration Rovers (MER) landings, the Descent Image Motion Estimation System (DIMES) was used for horizontal velocity estimation. The DIMES algorithm combines mea...
Yang Cheng, Andrew Edie Johnson, Larry Matthies
CVPR
2005
IEEE
14 years 7 months ago
A Generative Model of Human Hair for Hair Sketching
Human hair is a very complex visual pattern whose representation is rarely studied in the vision literature despite its important role in human recognition. In this paper, we prop...
Hong Chen, Song Chun Zhu
CVPR
2005
IEEE
14 years 7 months ago
Tone Reproduction: A Perspective from Luminance-Driven Perceptual Grouping
Hwann-Tzong Chen, Tyng-Luh Liu, Tien-Lung Chang