期刊
SIGNAL IMAGE AND VIDEO PROCESSING
卷 16, 期 4, 页码 937-945出版社
SPRINGER LONDON LTD
DOI: 10.1007/s11760-021-02038-6
关键词
Super-resolution; Convolutional neural network; Selective multi-scale network; Feature fusion
资金
- National Key Research and Development Program of China [2020YFB1711400]
- National Natural Science Foundation of China [52075485]
This paper aims to enhance the performance of single-image super-resolution (SISR) by introducing a selective multi-scale network (SMsN) model which combines selective multi-scale module (SMsM) and attentive global feature fusion (AGFF) scheme. The SMsN model outperforms some state-of-the-art SISR methods in terms of accuracy and efficiency, as demonstrated by extensive experimental results.
In this paper, we aim to improve the performance of single-image super-resolution (SISR) by designing a more effective feature extraction module and a better fusion scheme for integrating hierarchical features. Firstly, we propose a selective multi-scale module (SMsM) to adaptively aggregate multi-scale features via self-learned weights and thus extract more distinctive representation. Then, we design an attentive global feature fusion (AGFF) scheme to reduce the redundant information inside the extracted hierarchical features by employing a gate mechanism (in the form of group convolution) and adaptively re-calibrate the features with channel-wise attention weights before fusion. Stacked SMsMs and AGFF compose a novel network which is termed selective multi-scale network (SMsN). Extensive experimental results demonstrate that our SMsN model outperforms some state-of-the-art SISR methods in terms of accuracy and efficiency.
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