Next:
Abstract
Contents
Contributions to Parametric Image Registration and 3D Surface Reconstruction
Florent Brunet
Defended on 2010, November 30th at Université d'Auvergne
For the degree of Doctor of the Université d'Auvergne
Speciality: Computer Vision
President
Laurent Sarry
Co-Directors
Adrien Bartoli
Rémy Malgouyres
Nassir Navab
Reviewers
Lourdes Agapito
Joachim Hornegger
Étienne Mémin
Abstract
Abstract (in English)
Résumé (en Français)
Contents
List of Figures
List of Tables
Introduction
General Tools
Notation, First Definitions
Basics on Continuous Optimization
Parametric Models of Function
General Points on Parameter and Hyperparameter Estimation
Parameter Estimation
Hyperparameters
Range Surface Fitting
First Definitions and Concepts
The L-Tangent Norm
Range Surface Fitting with Heteroskedastic Noise
Image Registration
General Points on Image Registration
Direct Image Registration without Region of Interest
Pixel-Based Hyperparameter Selection for Feature-Based Image Registration
NURBS Warps
Introduction
Affine Interpretation of the BS-Warps
NURBS-Warps
Parameter Estimation
Experiments
Conclusion
Monocular Reconstruction of Inextensible Surfaces
Introduction
Related Work on Inextensible Surface Reconstruction
Convex Formulation of the Upper Bound Approach with Noise in all Images
Smooth and Inextensible Surface Reconstruction
Experimental Results
Conclusion
Conclusion
Feature-Driven Direct Non-Rigid Image Registration
Introduction
Problem Statement and Previous Work
Feature-Driven Registration
Local Registration Algorithms
Feature-Driven Warps
Experimental Results
Conclusions
Appendix: Learning-based Registration with a Piecewise Linear Model
Bibliography
About this document ...
Contributions to Parametric Image Registration and 3D Surface Reconstruction (Ph.D. dissertation, November 2010) - Florent Brunet
Webpage generated on July 2011
PDF version (11 Mo)
