arrow
返回

Double sparsity for multi-frame super resolution

delete2017-05-01
delete18
PRE
AI
T
Toshiyuki Kato
H
Hideitsu Hino *
N
Noboru Murata
DOI:10.1016/j.neucom.2017.02.043delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
A number of image super resolution algorithms based on the sparse coding have successfully implemented multi-frame super resolution in recent years. In order to utilize multiple low-resolution observations, both accurate image registration and sparse coding are required. Previous study on multi-frame super resolution based on sparse coding firstly apply block matching for image registration, followed by sparse coding to enhance the image resolution. In this paper, these two problems are solved by optimizing a single objective function. The proposed formulation not only has a mathematically interesting structure, called the double sparsity, but also yields comparable or improved numerical performance to conventional methods. (C) 2017 Elsevier B.V. All rights reserved.
Keyword:
Image Super Resolution
Sparse Coding
Double Sparsity
Dictionary Learning
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

W
Waseda University
学者数:
1.0W
论文数: 8.7K
被引数: 8.3K
U
University of Tsukuba
学者数:
1.8W
论文数: 1.5W
被引数: 1.7W
引用论文

引用论文

Multimodal Deep Autoencoder for Human Pose Recovery
err2015-12-01
err520
PREAI
errHong, Chaoqun; Yu, Jun; Wan, Jian; Tao, Dacheng; Wang, Meng
err分享
err收藏
Graph Regularized Sparsity Discriminant Analysis for face recognition用于人脸识别的图正则稀疏判别分析
err2016-01-01
err38
PREAI
errLou, Songjiang; Zhao, Xiaoming; Chuang, Yuelong; Yu, Haitao; Zhang, Shiqing
err分享
err收藏
学者 查看更多内容