Search For:

Displaying 1-17 out of 17 total
From Geometry to Variational Calculus: Theory and Applications of Three-Dimensional Vision
Found in: Computer Vision for Virtual Reality Based Human Communications, Workshop on
By Olivier Faugeras
Issue Date:January 1998
pp. 0052
We present some recent results on the we of geometric and variational techniques to solve problems in computer vision. The thrust of the paper is that a mathematical approach to problems is relevant, without necessarily giving up efficiency in applications...
 
Three Applications of GPU Computing in Neuroscience
Found in: Computing in Science & Engineering
By Javier Baladron,Diego Fasoli,Olivier Faugeras
Issue Date:May 2012
pp. 40-47
Three scenarios outlined here show the benefits of using a computer system with multiple GPUs in theoretical neuroscience. In each instance, it's clear that the GPU speedup considerably helps answer a scientific or technological question.
 
Shape Statistics for Image Segmentation with Prior
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Guillaume Charpiat, Olivier Faugeras, Renaud Keriven
Issue Date:June 2007
pp. 1-6
We propose a new approach to compute non-linear, intrinsic shape statistics and to incorporate them into a shape prior for an image segmentation task. Given a sample set of contours, we first define their mean shape as the one which is simultaneously close...
 
Reconciling Landmarks and Level Sets
Found in: Pattern Recognition, International Conference on
By Pierre Maurel, Renaud Keriven, Olivier Faugeras
Issue Date:August 2006
pp. 69-72
Shape warping is a key problem in statistical shape analysis. This paper proposes a framework for geometric shape warping based on both shape distances and landmarks. Our method is compatible with implicit representations and a matching between shape surfa...
 
Control Theory and Fast Marching Techniques for Brain Connectivity Mapping
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Emmanuel Prados, Stefano Soatto, Jean-Philippe Pons, Nicolas Wotawa, Rachid Deriche, Olivier Faugeras
Issue Date:June 2006
pp. 1076-1083
We propose a novel, fast and robust technique for the computation of anatomical connectivity in the brain. Our approach exploits the information provided by Diffusion Tensor Magnetic Resonance Imaging (or DTI) and models the white matter by using Riemannia...
 
Designing Spatially Coherent Minimizing Flows for Variational Problems Based on Active Contours
Found in: Computer Vision, IEEE International Conference on
By Guillaume Charpiat, Renaud Keriven, Jean-Philippe Pons, Olivier Faugeras
Issue Date:October 2005
pp. 1403-1408
This paper tackles an important aspect of the variational problems involving active contours, which has been largely overlooked so far: the optimization by gradient flows. Classically, the definition of a gradient depends directly on the choice of an inner...
 
Image Statistics Based on Diffeomorphic Matching
Found in: Computer Vision, IEEE International Conference on
By Guillaume Charpiat, Olivier Faugeras, Renaud Keriven
Issue Date:October 2005
pp. 852-857
We propose a new approach to deal with the first and second order statistics of a set of images. These statistics take into account the images characteristic deformations and their variations in intensity. The central algorithm is based on non-supervised d...
 
Modelling Dynamic Scenes by Registering Multi-View Image Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jean-Philippe Pons, Renaud Keriven, Olivier Faugeras
Issue Date:June 2005
pp. 822-827
In this paper, we present a new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences. Our method minimizes the prediction error of the shape and motion estimates. Both problems then ...
 
Shape Gradients for Histogram Segmentation using Active Contours
Found in: Computer Vision, IEEE International Conference on
By Stéphanie Jehan-Besson, Michel Barlaud, Gilles Aubert, Olivier Faugeras
Issue Date:October 2003
pp. 408
We consider the problem of image segmentation using active contours through the minimization of an energy criterion involving both region and boundary functionals. These functionals are derived through a shape derivative approach instead of classical calcu...
 
Revisiting Non-Parametric Activation Detection on fMRI Time Series
Found in: Mathematical Methods in Biomedical Image Analysis, IEEE Workshop on
By Bertrand Thirion, Olivier Faugeras
Issue Date:December 2001
pp. 121
In this paper, we propose some new ways of detecting activations in fMRI sequences that require a minimum of hypotheses and avoid any a priori modelling of the expected signal. In particular, we try to avoid linear assumptions and models. Instead, putting ...
 
Dense Image Matching with Global and Local Statistical Criteria: A Variational Approach
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Gerardo Hermosillo, Olivier Faugeras
Issue Date:December 2001
pp. 73
We present two new algorithms for multimodal, dense matching of two images using a variational approach. These algorithms complete and generalise our previous work by treating the case of semi-local energy functionals. In brief, they are derived from the m...
 
A Variational Approach to Multi-Modal Image Matching
Found in: Variational and Level Set Methods in Computer Vision, IEEE Workshop on
By Christophe Chefd'Hotel, Gerardo Hermosillo, Olivier Faugeras
Issue Date:July 2001
pp. 21
INRIAAbstract: We address the problem of non-parametric multi-modal image matching. We propose a generic framework which relies on a global variational formulation and show its versatility through three different multi-modal registration methods : supervis...
 
Statistical Shape Influence in Geodesic Active Contours
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael E. Leventon, W. Eric L. Grimson, Olivier Faugeras
Issue Date:June 2000
pp. 1316
A novel method of incorporating shape information into the image segmentation process is presented. We introduce a representation for deformable shapes and define a probability distribution over the variances of a set of training shapes. The segmentation p...
 
Codimension - Two Geodesic Active Contours for the Segmentation of Tubular Structures
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Liana M. Lorigo, W. Eric L. Grimson, Olivier Faugeras, Renaud Keriven, Ron Kikinis, Arya Nabavi, Carl-Fredrik Westin
Issue Date:June 2000
pp. 1444
Curve evolution schemes for segmentation, implemented with level set methods, have become an important approach in computer vision. Previous work has modeled evolving contours, which are curves in 2D or surfaces in 3D. Our objective is to explore recent ma...
 
3D Articulated Models and Multi-View Tracking with Silhouettes
Found in: Computer Vision, IEEE International Conference on
By Quentin Delamarre, Olivier Faugeras
Issue Date:September 1999
pp. 716
We propose a method to estimate the motion of a person filmed by two or more fixed cameras. The novelty of our technique is its ability to cope with fast movements, self-occlusions and noisy images. Our algorithms are based on the latest works on calibrati...
 
Algebraic and Geometric Tools to Compute Projective and Permutation Invariants
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gabriella Csurka, Olivier Faugeras
Issue Date:January 1999
pp. 58-65
<p><b>Abstract</b>—This paper studies the computation of projective invariants in pairs of images from uncalibrated cameras and presents a detailed study of the projective and permutation invariants for configurations of points and/or lin...
 
Self-Calibration of a 1D Projective Camera and Its Application to the Self-Calibration of a 2D Projective Camera
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Olivier Faugeras, Long Quan, Peter Strum
Issue Date:October 2000
pp. 1179-1185
<p><b>Abstract</b>—We introduce the concept of self-calibration of a 1D projective camera from point correspondences, and describe a method for uniquely determining the two internal parameters of a 1D camera, based on the trifocal tensor ...
 
 1