
Example-Based Super Resolution
Description
Key Features
- Provides detailed coverage of techniques and implementation details that have been successfully introduced in diverse and demanding real-world applications
- Covers a wide variety of machine learning approaches, ranging from cross-scale self-similarity concepts and sparse coding, to the latest advances in deep learning
- Presents a statistical interpretation of the subspace of natural image patches that transcends super resolution and makes it a valuable source for any researcher on image processing or low-level vision
Readership
Computer vision scientists and researchers with undergraduate-level statistics knowledge whose work is related to imaging. Machine learning, image processing, and research and development communities
Table of Contents
- Dedication
- List of Figures
- Acknowledgment
- Introduction
- The Super-Resolution Problem
- Super-Resolution Approaches
- Outline
- Chapter 1: Classic Multiframe Super Resolution
- Abstract
- 1.1 Problem Statement
- 1.2 Bayesian Inference
- 1.3 Interpolation-Based Methods
- 1.4 Performance Limits
- 1.5 Discussion
- Chapter 2: A Taxonomy of Example-Based Super Resolution
- Abstract
- 2.1 Example-Based Super Resolution
- 2.2 Internal Learning
- 2.3 External Learning
- 2.4 Discussion
- Chapter 3: High-Frequency Transfer
- Abstract
- 3.1 Adaptive Filter Selection
- 3.2 Robustness to Aliasing
- 3.3 Robustness to Noise
- 3.4 Discussion
- Chapter 4: Neighbor Embedding
- Abstract
- 4.1 Framework
- 4.2 Extensions
- 4.3 Performance
- 4.4 Discussion
- Chapter 5: Sparse Coding
- Abstract
- 5.1 Super Resolution Model
- 5.2 Adaptive Extension
- 5.3 Application
- 5.4 Discussion
- Chapter 6: Anchored Regression
- Abstract
- 6.1 Anchored Regression Framework
- 6.2 Extensions
- 6.3 Performance
- 6.4 Discussion
- Chapter 7: Trees and Forests
- Abstract
- 7.1 Hierarchical Manifold Learning
- 7.2 Naive Bayes Super-Resolution Forest
- 7.3 Performance
- 7.4 Discussion
- Chapter 8: Deep Learning
- Abstract
- 8.1 Neural networks
- 8.2 Networks for super resolution
- 8.3 Performance
- 8.4 Discussion
- Chapter 9: Conclusions
- Abstract
- 9.1 Overview
- 9.2 Perspective
- References
Product details
- No. of pages: 162
- Language: English
- Copyright: © Academic Press 2016
- Published: September 22, 2016
- Imprint: Academic Press
- Paperback ISBN: 9780128097038
- eBook ISBN: 9780081011355
About the Author
Jordi Salvador
PROVEC) and also to a European FP6 project (CHIL) as research assistant on multiview reconstruction. His research interests include 3D reconstruction, real-time and parallel algorithms, new computer-human interfaces, image and video restoration, super resolution, inverse problems and machine learning.
Affiliations and Expertise
Ratings and Reviews
There are currently no reviews for "Example-Based Super Resolution"