Sciweavers

CVPR
2007
IEEE
15 years 1 months ago
What makes a good model of natural images?
Many low-level vision algorithms assume a prior probability over images, and there has been great interest in trying to learn this prior from examples. Since images are very non G...
Yair Weiss, William T. Freeman
CVPR
2007
IEEE
15 years 1 months ago
Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention
A critical function in both machine vision and biological vision systems is attentional selection of scene regions worthy of further analysis by higher-level processes such as obj...
Robert J. Peters, Laurent Itti
CVPR
2007
IEEE
15 years 1 months ago
Using Geometry Invariants for Camera Response Function Estimation
In this paper, we present a new single-image camera response function (CRF) estimation method using geometry invariants (GI). We derive mathematical properties and geometric inter...
Tian-Tsong Ng, Shih-Fu Chang, Mao-Pei Tsui
CVPR
2007
IEEE
15 years 1 months ago
Color Constancy using Natural Image Statistics
Although many color constancy methods exist, they are all based on specific assumptions such as the set of possible light sources, or the spatial and spectral characteristics of i...
Arjan Gijsenij, Theo Gevers
CVPR
2007
IEEE
15 years 1 months ago
Modelling Objects using Distribution and Topology of Multiscale Region Pairs
We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this ...
Himanshu Arora, Narendra Ahuja
CVPR
2007
IEEE
15 years 1 months ago
Flexible Object Models for Category-Level 3D Object Recognition
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Akash Kushal, Cordelia Schmid, Jean Ponce
CVPR
2007
IEEE
15 years 1 months ago
Simultaneous Covariance Driven Correspondence (CDC) and Transformation Estimation in the Expectation Maximization Framework
This paper proposes a new registration algorithm, Covariance Driven Correspondences (CDC), that depends fundamentally on the estimation of uncertainty in point correspondences. Th...
Michal Sofka, Gehua Yang, Charles V. Stewart
CVPR
2007
IEEE
15 years 1 months ago
Topology Preserving Log-Unbiased Nonlinear Image Registration: Theory and Implementation
In this paper, we present a novel framework for constructing large deformation log-unbiased image registration models that generate theoretically and intuitively correct deformati...
Igor Yanovsky, Paul M. Thompson, Stanley Osher, Al...
CVPR
2007
IEEE
15 years 1 months ago
The Hyperbolic Geometry of Illumination-Induced Chromaticity Changes
The non-negativity of color signals implies that they span a conical space with a hyperbolic geometry. We use perspective projections to separate intensity from chromaticity, and ...
Reiner Lenz, Pedro Latorre Carmona, Peter Meer