Neighborhood issue in single-frame image Super-Resolution

Kevin Su; Qi Tian; Qing Xue; Nicu Sebe; Jingsheng Ma

doi:10.1109/ICME.2005.1521623

Neighborhood issue in single-frame image Super-Resolution

Kevin Su, Qi Tian, Qing Xue, Nicu Sebe, Jingsheng Ma

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

73 Citations (Scopus)

Abstract

Super-Resolution is the problem of generating one or a set of high resolution images from one or a sequence of low-resolution frames. Most methods have been proposed for super-resolution based on multiple low resolution images of the same scene, which is called multiple-frame super-resolution. Only a few approaches produce a high-resolution image from a single low-resolution image, with the help of one or a set of training images from scenes of the same or different types. It is referred to as single-frame super-resolution. This article reviews a variety of single-frame Super-Resolution methods proposed in the recent years. In the paper, a new manifold learning method: locally linear embedding (LLE) and its relation with single-frame superresolution is introduced. Detailed study of a critical issue: "Neighborhood Issue" is presented with related experimental results and analysis. And possible future research is given. © 2005 IEEE.

Original language	English
Title of host publication	IEEE International Conference on Multimedia and Expo, ICME 2005
Pages	1122-1125
Number of pages	4
Volume	2005
DOIs	https://doi.org/10.1109/ICME.2005.1521623
Publication status	Published - 2005
Event	IEEE International Conference on Multimedia and Expo - Amsterdam, Netherlands Duration: 6 Jul 2005 → 8 Jul 2005

Conference

Conference	IEEE International Conference on Multimedia and Expo
Abbreviated title	ICME 2005
Country/Territory	Netherlands
City	Amsterdam
Period	6/07/05 → 8/07/05

Access to Document

10.1109/ICME.2005.1521623

Cite this

@inproceedings{4b30ae0ad3224d1da3944ff5a8ebc0c3,

title = "Neighborhood issue in single-frame image Super-Resolution",

abstract = "Super-Resolution is the problem of generating one or a set of high resolution images from one or a sequence of low-resolution frames. Most methods have been proposed for super-resolution based on multiple low resolution images of the same scene, which is called multiple-frame super-resolution. Only a few approaches produce a high-resolution image from a single low-resolution image, with the help of one or a set of training images from scenes of the same or different types. It is referred to as single-frame super-resolution. This article reviews a variety of single-frame Super-Resolution methods proposed in the recent years. In the paper, a new manifold learning method: locally linear embedding (LLE) and its relation with single-frame superresolution is introduced. Detailed study of a critical issue: {"}Neighborhood Issue{"} is presented with related experimental results and analysis. And possible future research is given. {\textcopyright} 2005 IEEE.",

author = "Kevin Su and Qi Tian and Qing Xue and Nicu Sebe and Jingsheng Ma",

year = "2005",

doi = "10.1109/ICME.2005.1521623",

language = "English",

isbn = "0780393325",

volume = "2005",

pages = "1122--1125",

booktitle = "IEEE International Conference on Multimedia and Expo, ICME 2005",

note = "IEEE International Conference on Multimedia and Expo, ICME 2005 ; Conference date: 06-07-2005 Through 08-07-2005",

}

TY - GEN

T1 - Neighborhood issue in single-frame image Super-Resolution

AU - Su, Kevin

AU - Tian, Qi

AU - Xue, Qing

AU - Sebe, Nicu

AU - Ma, Jingsheng

PY - 2005

Y1 - 2005

N2 - Super-Resolution is the problem of generating one or a set of high resolution images from one or a sequence of low-resolution frames. Most methods have been proposed for super-resolution based on multiple low resolution images of the same scene, which is called multiple-frame super-resolution. Only a few approaches produce a high-resolution image from a single low-resolution image, with the help of one or a set of training images from scenes of the same or different types. It is referred to as single-frame super-resolution. This article reviews a variety of single-frame Super-Resolution methods proposed in the recent years. In the paper, a new manifold learning method: locally linear embedding (LLE) and its relation with single-frame superresolution is introduced. Detailed study of a critical issue: "Neighborhood Issue" is presented with related experimental results and analysis. And possible future research is given. © 2005 IEEE.

AB - Super-Resolution is the problem of generating one or a set of high resolution images from one or a sequence of low-resolution frames. Most methods have been proposed for super-resolution based on multiple low resolution images of the same scene, which is called multiple-frame super-resolution. Only a few approaches produce a high-resolution image from a single low-resolution image, with the help of one or a set of training images from scenes of the same or different types. It is referred to as single-frame super-resolution. This article reviews a variety of single-frame Super-Resolution methods proposed in the recent years. In the paper, a new manifold learning method: locally linear embedding (LLE) and its relation with single-frame superresolution is introduced. Detailed study of a critical issue: "Neighborhood Issue" is presented with related experimental results and analysis. And possible future research is given. © 2005 IEEE.

UR - https://www.scopus.com/pages/publications/33750557616

U2 - 10.1109/ICME.2005.1521623

DO - 10.1109/ICME.2005.1521623

M3 - Conference contribution

SN - 0780393325

SN - 9780780393325

VL - 2005

SP - 1122

EP - 1125

BT - IEEE International Conference on Multimedia and Expo, ICME 2005

T2 - IEEE International Conference on Multimedia and Expo

Y2 - 6 July 2005 through 8 July 2005

ER -

Neighborhood issue in single-frame image Super-Resolution

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this