Cargando…
Example-based Super Resolution.
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
London :
Academic Press,
2017.
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Front Cover; Example-Based Super Resolution; Copyright; Dedication; Contents; List of Figures; Acknowledgment; Introduction; The Super-Resolution Problem; Super-Resolution Approaches; Interpolation; Multiframe Super Resolution; Example-Based Super Resolution; Outline; About the Book; Chapter 1: Classic Multiframe Super Resolution; 1.1 Problem Statement; 1.1.1 A Frequency-Domain Pipeline; 1.2 Bayesian Inference; 1.2.1 Maximum Likelihood; 1.2.2 Maximum A Posteriori; 1.3 Interpolation-Based Methods; 1.3.1 Registration; 1.3.2 Warping Projection; Forward Warping; Backward Warping.
- 1.3.3 RestorationInpainting; Deblurring; Denoising; Iterative Reconstruction; 1.4 Performance Limits; 1.5 Discussion; Chapter 2: A Taxonomy of Example-Based Super Resolution; 2.1 Example-Based Super Resolution; 2.1.1 Parametric Methods; 2.1.2 Nonparametric Methods; 2.2 Internal Learning; 2.2.1 High-Frequency Transfer; 2.2.2 Neighbor Embedding; 2.3 External Learning; 2.3.1 Sparse Coding; 2.3.2 Anchored Regression; 2.3.3 Regression Trees; 2.3.4 Deep Learning; 2.4 Discussion; Chapter 3: High-Frequency Transfer; 3.1 Adaptive Filter Selection; 3.1.1 Parametric Filter Design; Implementation Notes.
- 3.1.2 Performance3.2 Robustness to Aliasing; 3.2.1 Local Regularization; High-Contrast Edge Detection, Dilation and Scaling; Local Denoising; Locally Regularized HF Synthesis; 3.2.2 Performance; 3.3 Robustness to Noise; 3.3.1 In-Place Cross-Scale Self-Similarity; In-place Structure Similarity; Noisy In-place Self-Similarity; 3.3.2 Iterative Noise-Aware Super Resolution; Interpolation; Analysis; Learning; Reconstruction; Implementation Details; 3.3.3 Performance; Processing Time; 3.4 Discussion; Chapter 4: Neighbor Embedding; 4.1 Framework; 4.1.1 Problem Statement.
- 4.1.2 Internal vs. External LearningInternal Learning; External Learning; 4.2 Extensions; 4.2.1 Multiphase Neighbor Embeddings; Pipeline; Complexity; 4.2.2 Nonnegative Least Squares; Features; Method; 4.3 Performance; 4.3.1 Configuration; Internal vs. External Learning; 4.3.2 Benchmark; 4.4 Discussion; Chapter 5: Sparse Coding; 5.1 Super Resolution Model; 5.1.1 Sparse Reconstruction; 5.1.2 Dictionary Training; Joint Training; Single-Scale Training; 5.2 Adaptive Extension; 5.2.1 Training Region Selection; 5.2.2 Region Rejection; 5.3 Application; 5.3.1 Feature Space; 5.3.2 Performance.
- Training and Testing SetsComparison With Other Methods; 5.4 Discussion; Chapter 6: Anchored Regression; 6.1 Anchored Regression Framework; 6.1.1 Problem Statement; 6.1.2 Anchored Neighbors; 6.1.3 Inference by Linear Regression; Features; 6.2 Extensions; 6.2.1 Improved Accuracy; 6.2.2 Improved Runtime; 6.3 Performance; 6.3.1 Implementation Details; Coarse Approximation; Feature Vectors; Supervised Learning; Hashing; 6.3.2 Benchmarking; Quality; Computational Cost; 6.4 Discussion; Chapter 7: Trees and Forests; 7.1 Hierarchical Manifold Learning; Contrast Normalization; Unimodal Trees.