Upsampling Attention Network for Single Image Super-resolution

Zhijie Zheng, Zhijie Zheng, Zhijie Zheng, Yuhang Jiao, Guangyou Fang, Guangyou Fang, Guangyou Fang

2021

Abstract

Recently, convolutional neural network (CNN) has been widely used in single image super-resolution (SISR) and made significant advances. However, most of the existing CNN-based SISR models ignore fully utilization of the extracted features during upsampling, causing information bottlenecks, hence hindering the expressive ability of networks. To resolve these problems, we propose an upsampling attention network (UAN) for richer feature extraction and reconstruction. Specifically, we present a residual attention groups (RAGs) based structure to extract structural and frequency information, which is composed of several residual feature attention blocks (RFABs) with a non-local skip connection. Each RFAB adaptively rescales spatial- and channel-wise features by paying attention to correlations among them. Furthermore, we propose an upsampling attention block (UAB), which not only applies parallel upsampling processes to obtain richer feature representations, but also combines them to obtain better reconstruction results. Experiments on standard benchmarks show the advantage of our UAN over state-of-the-art methods both in objective metrics and visual qualities.

Paper Citation

in Harvard Style

Zheng Z., Jiao Y. and Fang G. (2021). Upsampling Attention Network for Single Image Super-resolution. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 399-406. DOI: 10.5220/0010283603990406

in Bibtex Style

@conference{visapp21,
author={Zhijie Zheng and Yuhang Jiao and Guangyou Fang},
title={Upsampling Attention Network for Single Image Super-resolution},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={399-406},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010283603990406},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Upsampling Attention Network for Single Image Super-resolution
SN - 978-989-758-488-6
AU - Zheng Z.
AU - Jiao Y.
AU - Fang G.
PY - 2021
SP - 399
EP - 406
DO - 10.5220/0010283603990406
PB - SciTePress