Jump to content
Manifold Learning for Super Resolution / Titelei/Inhaltsverzeichnis
Manifold Learning for Super Resolution / Titelei/Inhaltsverzeichnis
Contents
Chapter
Expand
|
Collapse
Page
Titelei/Inhaltsverzeichnis
Details
1–12
1 Introduction
1–12
Details
1.1 Problem statement
Details
1.2 Motivation
Details
1.3 Challenges
Details
1.4 Related work
Details
1.5 Contributions
Details
1.6 Overview
Details
1.7 Author’s papers
Details
13–22
2 Sparse dictionaries for SR
13–22
Details
2.1 Introduction
Details
2.2 Model for Sparse SR
Details
2.3 Global Reconstruction Constrain
Details
2.4 Training coupled dictionaries
Details
2.5 Efficient sparse SR
Details
2.5.1 k-SVD
Details
2.6 Summary and discussion
Details
23–27
3 Anchored Neighborhood Regression
23–27
Details
3.1 Introduction
Details
3.2 Collaborative Norm Relaxation
Details
3.3 Neighborhood Embedding
Details
3.4 Summary and discussion
Details
28–32
4 Bayesian approach to adaptive dictionaries
28–32
Details
4.1 Introduction
Details
4.2 Adaptive Training Set
Details
4.3 Bayesian Formulation
Details
4.4 Rejecting Non-Informative Regions
Details
4.5 Feature Space
Details
4.6 Summary and discussion
Details
33–39
5 Dense Local Training and Spherical Hashing
33–39
Details
5.1 Introduction
Details
5.2 Linear Regression Framework
Details
5.3 Neighborhoods and training
Details
5.4 Search Strategy
Details
5.5 Summary and discussion
Details
40–51
6 Half-Hypersphere Confinement
40–51
Details
6.1 Introduction
Details
6.2 Metrics for linear regression
Details
6.3 Embedding in the Euclidean Space
Details
6.4 Feature Space and coarse approximation
Details
6.5 Validation
Details
6.6 Summary and discussion
Details
52–57
7 Naive Bayes SR Forest
52–57
Details
7.1 Introduction
Details
7.2 Hierarchical manifold learning
Details
7.3 Antipodality and bimodal trees
Details
7.4 Naive Bayes Super-Resolution Forest
Details
7.5 Von Mises-Fisher distribution
Details
7.6 Local Naive Bayes tree selection
Details
7.7 Validation
Details
7.8 Summary and discussion
Details
58–67
8 Dihedral Symmetry Collapse
58–67
Details
8.1 Introduction
Details
8.2 Reducing the manifold span
Details
8.2.1 Mean subtraction and normalization
Details
8.2.2 Antipodality
Details
8.2.3 Transformation models
Details
8.2.4 Dihedral group in the DCT space
Details
8.3 Manifold symmetries
Details
8.4 Application to SR
Details
8.5 Validation
Details
8.6 Summary and discussion
Details
68–101
9 Results
68–101
Details
9.1 Methodology
Details
9.2 Metrics
Details
9.2.1 Peak Signal-to-Noise Ratio
Details
9.2.2 SSIM
Details
9.2.3 IFC
Details
9.2.4 Time
Details
9.2.5 Model Size
Details
9.3 Datasets
Details
9.4 Sparse SR
Details
9.5 Anchored Neighborhood Regression
Details
9.6 Adaptive dictionaries
Details
9.7 Dense Local Training
Details
9.8 Half Hypersphere Confinement
Details
9.9 Naive Bayes SR Forest
Details
9.10 Patch Symmetry Collapse
Details
9.11 Benchmarking
Details
102–105
10 Conclusions
102–105
Details
10.1 Future Work
Details
106–118
Bibliography
106–118
Details
Durchsuchen Sie das Werk
Geben Sie ein Keyword in die Suchleiste ein
Partial access
Manifold Learning for Super Resolution
Titelei/Inhaltsverzeichnis
Autoren
Eduardo Pérez Pellitero
DOI
doi.org/10.51202/9783186859105-I
ISBN print: 978-3-18-385910-8
ISBN online: 978-3-18-685910-5
Chapter Preview
Share
Download PDF
Download citation
RIS
BibTeX
Copy DOI link
doi.org/10.51202/9783186859105-I
Share by email
Video schließen
Share by email VDI Verlag eLibrary
Recipient*
Sender*
Message*
Your name
Send message
This site is protected by reCAPTCHA and the Google
Privacy Policy
and
Terms of Service
apply.
