Manifold Learning for Super Resolution

Eduardo Pérez Pellitero

doi:10.51202/9783186859105

Keywords

Search publication

Bibliographic data

Copyright year: 2018
ISBN-Print: 978-3-18-385910-8
ISBN-Online: 978-3-18-685910-5
Publisher: VDI Verlag, Düsseldorf
Series: Informatik/ Kommunikation
Volume: 859
Language: German
Pages: 118
Product type: Book Titles

Titelei/Inhaltsverzeichnis Partial access Pages I - XII Download chapter (PDF)
1. Problem statement No access
2. Motivation No access
3. Challenges No access
4. Related work No access
5. Contributions No access
6. Overview No access
7. Author’s papers No access
1. Introduction No access
2. Model for Sparse SR No access
3. Global Reconstruction Constrain No access
4. Training coupled dictionaries No access
5. 1. k-SVD No access
6. Summary and discussion No access
1. Introduction No access
2. Collaborative Norm Relaxation No access
3. Neighborhood Embedding No access
4. Summary and discussion No access
1. Introduction No access
2. Adaptive Training Set No access
3. Bayesian Formulation No access
4. Rejecting Non-Informative Regions No access
5. Feature Space No access
6. Summary and discussion No access
1. Introduction No access
2. Linear Regression Framework No access
3. Neighborhoods and training No access
4. Search Strategy No access
5. Summary and discussion No access
1. Introduction No access
2. Metrics for linear regression No access
3. Embedding in the Euclidean Space No access
4. Feature Space and coarse approximation No access
5. Validation No access
6. Summary and discussion No access
1. Introduction No access
2. Hierarchical manifold learning No access
3. Antipodality and bimodal trees No access
4. Naive Bayes Super-Resolution Forest No access
5. Von Mises-Fisher distribution No access
6. Local Naive Bayes tree selection No access
7. Validation No access
8. Summary and discussion No access
1. Introduction No access
2. 1. Mean subtraction and normalization No access
  2. Antipodality No access
  3. Transformation models No access
  4. Dihedral group in the DCT space No access
3. Manifold symmetries No access
4. Application to SR No access
5. Validation No access
6. Summary and discussion No access
1. Methodology No access
2. 1. Peak Signal-to-Noise Ratio No access
  2. SSIM No access
  3. IFC No access
  4. Time No access
  5. Model Size No access
3. Datasets No access
4. Sparse SR No access
5. Anchored Neighborhood Regression No access
6. Adaptive dictionaries No access
7. Dense Local Training No access
8. Half Hypersphere Confinement No access
9. Naive Bayes SR Forest No access
10. Patch Symmetry Collapse No access
11. Benchmarking No access
1. Future Work No access
Bibliography No access Pages 106 - 118