期刊
INFORMATION SCIENCES
卷 462, 期 -, 页码 315-330出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2018.06.030
关键词
Single image super-resolution; Hadamard transform; Decision tree
资金
- National Science Foundation of China [61300135]
- Pearl River Technology Nova Project [201710010020]
- Fundamental Research Funds for the Central Universities [x2rjD2153900]
- Hong Kong Scholars Program [XJ2014058]
- Open Project Program of the State Key Lab of CAD CG Grant [A1619]
Image super-resolution (SR) has extensive applications in surveillance systems, satellite imaging, medical imaging, and ultra-high definition display devices. However, state-of-the-art methods for SR still incur considerable running times. In this paper, we thus propose a method based on the Hadamard pattern and tree search structure to significantly reduce the running time. In this approach, low-resolution (LR) and high-resolution (HR) training patch pairs are classified into different classes based on the Hadamard patterns generated from the LR training patches. The mapping relationship between the LR space and the HR space for each class is then learned and used for SR. Experimental results show that the proposed method can achieve an accuracy comparable to those of state-of-the-art methods with a much faster running speed. The dataset, pretrained models and source code can be accessed at the URL in the footnote(2). (C) 2018 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据