Manifold Learning for Super Resolution

Research output: Book/Report › Monograph › Research › peer review

Authors

  • Eduardo Pérez Pellitero

Research Organisations

View graph of relations

Details

Original languageGerman
Place of PublicationDüsseldorf
Number of pages114
Edition1
ISBN (electronic)9783186859105
Publication statusPublished - 2018

Publication series

NameInformatik/ Kommunikation
Volume859
ISSN (Print)0178-9627

Abstract

The development pace of high-resolution displays has been so fast in the recent years that many images acquired with low-end capture devices are already outdated or will be shortly in time. Super Resolution is central to match the resolution of the already existing image content to that of current and future high resolution displays and applications. This dissertation is focused on learning how to upscale images from the statistics of natural images. We build on a sparsity model that uses learned coupled low- and high-resolution dictionaries in order to upscale images, and move towards a more efficient L2 regularization scheme. Instead of using a patch-todictionary decomposition, we propose a fully collaborative neighbor embedding approach. We study the positive impact of antipodally invariant metrics for linear regression frameworks, and extend them by also taking into consideration the dihedral group of transforms (i.e. rotations and reflections), as a group of symmetries within the

Cite this

Manifold Learning for Super Resolution. / Pérez Pellitero, Eduardo.
1 ed. Düsseldorf, 2018. 114 p. (Informatik/ Kommunikation; Vol. 859).

Research output: Book/Report › Monograph › Research › peer review

Pérez Pellitero, E 2018, Manifold Learning for Super Resolution. Informatik/ Kommunikation, vol. 859, 1 edn, Düsseldorf. https://doi.org/10.51202/9783186859105
Pérez Pellitero, E. (2018). Manifold Learning for Super Resolution. (1 ed.) (Informatik/ Kommunikation; Vol. 859). https://doi.org/10.51202/9783186859105
Pérez Pellitero E. Manifold Learning for Super Resolution. 1 ed. Düsseldorf, 2018. 114 p. (Informatik/ Kommunikation). doi: 10.51202/9783186859105
Pérez Pellitero, Eduardo. / Manifold Learning for Super Resolution. 1 ed. Düsseldorf, 2018. 114 p. (Informatik/ Kommunikation).
Download
@book{152a5c767c3e417faffbb6b806b5db10,
title = "Manifold Learning for Super Resolution",
abstract = "The development pace of high-resolution displays has been so fast in the recent years that many images acquired with low-end capture devices are already outdated or will be shortly in time. Super Resolution is central to match the resolution of the already existing image content to that of current and future high resolution displays and applications. This dissertation is focused on learning how to upscale images from the statistics of natural images. We build on a sparsity model that uses learned coupled low- and high-resolution dictionaries in order to upscale images, and move towards a more efficient L2 regularization scheme. Instead of using a patch-todictionary decomposition, we propose a fully collaborative neighbor embedding approach. We study the positive impact of antipodally invariant metrics for linear regression frameworks, and extend them by also taking into consideration the dihedral group of transforms (i.e. rotations and reflections), as a group of symmetries within the",
keywords = "Super Resolution, Manifold Learning, Inverse Problems, Computer Vision Image Processing, Machine Learning, Upscaling",
author = "{P{\'e}rez Pellitero}, Eduardo",
year = "2018",
doi = "10.51202/9783186859105",
language = "Deutsch",
isbn = "978-3-18-385910-8",
series = "Informatik/ Kommunikation",
edition = "1",

}

Download

TY - BOOK

T1 - Manifold Learning for Super Resolution

AU - Pérez Pellitero, Eduardo

PY - 2018

Y1 - 2018

N2 - The development pace of high-resolution displays has been so fast in the recent years that many images acquired with low-end capture devices are already outdated or will be shortly in time. Super Resolution is central to match the resolution of the already existing image content to that of current and future high resolution displays and applications. This dissertation is focused on learning how to upscale images from the statistics of natural images. We build on a sparsity model that uses learned coupled low- and high-resolution dictionaries in order to upscale images, and move towards a more efficient L2 regularization scheme. Instead of using a patch-todictionary decomposition, we propose a fully collaborative neighbor embedding approach. We study the positive impact of antipodally invariant metrics for linear regression frameworks, and extend them by also taking into consideration the dihedral group of transforms (i.e. rotations and reflections), as a group of symmetries within the

AB - The development pace of high-resolution displays has been so fast in the recent years that many images acquired with low-end capture devices are already outdated or will be shortly in time. Super Resolution is central to match the resolution of the already existing image content to that of current and future high resolution displays and applications. This dissertation is focused on learning how to upscale images from the statistics of natural images. We build on a sparsity model that uses learned coupled low- and high-resolution dictionaries in order to upscale images, and move towards a more efficient L2 regularization scheme. Instead of using a patch-todictionary decomposition, we propose a fully collaborative neighbor embedding approach. We study the positive impact of antipodally invariant metrics for linear regression frameworks, and extend them by also taking into consideration the dihedral group of transforms (i.e. rotations and reflections), as a group of symmetries within the

KW - Super Resolution

KW - Manifold Learning

KW - Inverse Problems

KW - Computer Vision Image Processing

KW - Machine Learning

KW - Upscaling

U2 - 10.51202/9783186859105

DO - 10.51202/9783186859105

M3 - Monografie

SN - 978-3-18-385910-8

T3 - Informatik/ Kommunikation

BT - Manifold Learning for Super Resolution

CY - Düsseldorf

ER -