Sciweavers

CVPR
2000
IEEE
14 years 11 months ago
On the Number of Samples Needed in Light Field Rendering with Constant-Depth Assumption
While several image-based rendering techniques have been proposed to successfully render scenes/objects from a large collection (e.g., thousands) of images without explicitly reco...
Zhouchen Lin, Heung-Yeung Shum
CVPR
2000
IEEE
14 years 11 months ago
Zebra-Crossing Detection for the Partially Sighted
Zebra-crossings are useful road features for outdoor navigation in mobility aids for the partially sighted. In this paper, zebra-crossings are detected by looking for groups of co...
Stephen Se
CVPR
2000
IEEE
14 years 11 months ago
Codimension - Two Geodesic Active Contours for the Segmentation of Tubular Structures
Curve evolution schemes for segmentation, implemented with level set methods, have become an important approach in computer vision. Previous work has modeled evolving contours whi...
Liana M. Lorigo, W. Eric L. Grimson, Olivier D. Fa...
CVPR
2000
IEEE
14 years 11 months ago
Visual Websearching Using Iconic Queries
Imagine a professional Web site designer who constantly has to come up with innovative looks for the client's homepages? How does he find the new content? The major search en...
Michael S. Lew, Nicu Sebe
CVPR
2000
IEEE
14 years 11 months ago
Improving Visual Matching
Many visual matching algorithms can be described in terms of the features and the inter-feature distance or metric. The most commonly used metric is the sum of squared di erences ...
Michael S. Lew, Nicu Sebe, Thomas S. Huang
CVPR
2000
IEEE
14 years 11 months ago
Edge-Constrained Joint View Triangulation for Image Interpolation
Image-based-interpolation creates smooth and photorealistic views between two view points. The concept of joint view triangulation (JVT) has been proven to be an efficient multi-v...
Maxime Lhuillier, Long Quan
CVPR
2000
IEEE
14 years 11 months ago
A Semi-Automatic Method for Resolving Occlusion in Augmented Reality
Realistic merging of virtual and real objects requires that the augmented patterns be correctly occluded by foreground objects. In this paper, we propose a semi-automatic method f...
Vincent Lepetit, Marie-Odile Berger
CVPR
2000
IEEE
14 years 11 months ago
Shape Descriptors for Non-Rigid Shapes with a Single Closed Contour
Longin Jan Latecki, Rolf Lakämper, Ulrich Eck...
CVPR
2000
IEEE
14 years 11 months ago
Statistical cues for Domain Specific Image Segmentation with Performance Analysis
This paper investigates the use of colour and texture cues for segmentation of images within two specified domains. The first is the Sowerby dataset, which contains one hundred co...
Scott Konishi, Alan L. Yuille