Next:
List of Figures
Up:
Contributions to Parametric Image
Previous:
Résumé (en Français)
Contents
List of Figures
List of Tables
Introduction
General Tools
Notation, First Definitions
Basic Notations
Functions
Sets and Collections
Matrices and Vectors
Other Common Notation
Basics on Continuous Optimization
Generalities on Optimization
Optimization Algorithms
Parametric Models of Function
Splines
The B-spline Representation
Non Uniform Rational B-Splines (NURBS)
Radial Basis Functions
General Points on Parameter and Hyperparameter Estimation
Parameter Estimation
General Points on Parameter Estimation
Specific Techniques in Parameter Estimation
Hyperparameters
Generalities
Automatic Computation of the Hyperparameters
Range Surface Fitting
First Definitions and Concepts
First Definitions
Acquisition of Range Data
An Introductory Example
The L-Tangent Norm
Supplementary Details on Range Surface Fitting
The L-Curve Criterion
The L-Tangent Norm Criterion
Experimental Results
Range Surface Fitting with Heteroskedastic Noise
Fitting a B-spline on Mesh Data
Our Approach to Handle Heteroskedastic Noise and Discontinuities
Experiments
Image Registration
General Points on Image Registration
Background
Problem Statement
Direct Image Registration without Region of Interest
Introduction
Region of Interest: State of the Art
Direct Image Registration without Region of Interest
Experimental Results
Conclusion
Pixel-Based Hyperparameter Selection for Feature-Based Image Registration
Introduction
Reminder and Complementary Elements on Automatic Hyperparameter Selection
Our Contribution: the Photometric Error Criterion
Experimental Results
Conclusion
NURBS Warps
Introduction
Affine Interpretation of the BS-Warps
NURBS-Warps
Parameter Estimation
The BS-Warp
The NURBS-Warp
Experiments
Simulated Data
Real Images
Conclusion
Monocular Template-based Reconstruction of Smooth and Inextensible Surfaces
Introduction
Related Work on Inextensible Surface Reconstruction
Convex Formulation of the Upper Bound Approach with Noise in all Images
Noise in the Template Only
Noise in Both the Template and the Input Images
Smooth and Inextensible Surface Reconstruction
Parametric Surface Model
Surface Reconstruction as a Least-Squares Problem
Experimental Results
Experiments on Synthetic Data
Experiments on Real Data
Conclusion
Conclusion
Feature-Driven Direct Non-Rigid Image Registration
Introduction
Problem Statement and Previous Work
Forward Additive Algorithms
Inverse Compositional Algorithms
Feature-Driven Registration
Feature-Driven Warp Parameterization
Threading Warps
Reverting Warps
Compositional Feature-Driven Registration
Local Registration Algorithms
Local Registration with Gauss-Newton
Learning-Based Local Registration
Feature-Driven Warps
The Feature-Driven Thin-Plate Spline Warp
The Feature-Driven Free-Form Deformation
Experimental Results
Representational Similarity of the TPS and FFD Warps
Comparison of Registration Algorithms
Conclusions
Framework
Experimental Results
Bibliography
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)