Sciweavers

ICCV
2007
IEEE
13 years 11 months ago
Scale-Dependent 3D Geometric Features
Three-dimensional geometric data play fundamental roles in many computer vision applications. However, their scale-dependent nature, i.e. the relative variation in the spatial ext...
John Novatnack, Ko Nishino
ICCV
2007
IEEE
13 years 11 months ago
Curvature Estimation for Enhancement of Crossing Curves
In this paper we describe a method for estimating curvature of elongated structures in images. The curvature estimation is performed on an invertible orientation score, which is a...
Erik Franken, Remco Duits, Bart M. ter Haar Romeny
ICCV
2007
IEEE
13 years 11 months ago
Simultaneous Segmentation and 3D Reconstruction of Monocular Image Sequences
When trying to extract 3D scene information and camera motion from an image sequence alone, it is often necessary to cope with independently moving objects. Recent research has un...
Kemal Egemen Ozden, Konrad Schindler, Luc J. Van G...
ICCV
2007
IEEE
13 years 11 months ago
Dense Multiscale Motion Extraction from Cardiac Cine MR Tagging using HARP Technology
We propose an operational method to extract the left ventricle (LV) systole dynamics using HARmonic Phase (HARP) images extracted from tagged cardiac MR sequences. Established tec...
Luc Florack, Hans C. van Assen, Avan Suinesiaputra
ICCV
2007
IEEE
13 years 11 months ago
Toward a Theory of Shape from Specular Flow
The image of a curved, specular (mirror-like) surface is a distorted reflection of the environment. The goal of our work is to develop a framework for recovering general shape fr...
Yair Adato, Yuriy Vasilyev, Ohad Ben-Shahar, Todd ...
ICCV
2007
IEEE
13 years 11 months ago
Shape Priors using Manifold Learning Techniques
We introduce a non-linear shape prior for the deformable model framework that we learn from a set of shape samples using recent manifold learning techniques. We model a category o...
Patrick Etyngier, Florent Ségonne, Renaud K...
ICCV
2007
IEEE
13 years 11 months ago
Non-Rigid Object Alignment with a Mismatch Template Based on Exhaustive Local Search
Non-rigid object alignment is especially challenging when only a single appearance template is available and target and template images fail to match. Two sources of discrepancy b...
Yang Wang, Simon Lucey, Jeffrey F. Cohn
ICCV
2007
IEEE
13 years 11 months ago
Multispectral Imaging Using Multiplexed Illumination
Many vision tasks such as scene segmentation, or the recognition of materials within a scene, become considerably easier when it is possible to measure the spectral reflectance o...
Jong-Il Park, Moon-Hyun Lee, Michael D. Grossberg,...
ICCV
2007
IEEE
13 years 11 months ago
Surface-from-Gradients with Incomplete Data for Single View Modeling
Surface gradients are useful to surface reconstruction in single view modeling, shape-from-shading, and photometric stereo. Previous algorithms minimize a complex, nonlinear energ...
Heung-Sun Ng, Tai-Pang Wu, Chi-Keung Tang
ICCV
2007
IEEE
13 years 11 months ago
Non-homogeneous Content-driven Video-retargeting
Video retargeting is the process of transforming an existing video to fit the dimensions of an arbitrary display. A compelling retargeting aims at preserving the viewers’ exper...
Lior Wolf, Moshe Guttmann, Daniel Cohen-Or