Next Article in Journal
Outdoor Particulate Matter Correlation Analysis and Prediction Based Deep Learning in the Korea
Previous Article in Journal
Radar Signal Sorting Method Based on Radar Coherent Characteristic
Open AccessArticle

Perceptual Metric Guided Deep Attention Network for Single Image Super-Resolution

Jiangsu Key Laboratory of Big Data Analysis Technology, Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, China
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(7), 1145; https://doi.org/10.3390/electronics9071145
Received: 16 June 2020 / Revised: 11 July 2020 / Accepted: 13 July 2020 / Published: 15 July 2020
(This article belongs to the Section Artificial Intelligence)
Deep learning has been widely applied to image super-resolution (SR) tasks and has achieved superior performance over traditional methods due to its excellent feature learning capabilities. However, most of these deep learning-based methods require training image sets to pre-train SR network parameters. In this paper, we propose a new single image SR network without the need of any pre-training. The proposed network is optimized to achieve the SR reconstruction only from a low resolution observation rather than training image sets, and it focuses on improving the visual quality of reconstructed images. Specifically, we designed an attention-based decoder-encoder network for predicting the SR reconstruction, in which a residual spatial attention (RSA) unit is deployed in each layer of decoder to capture key information. Moreover, we adopt the perceptual metric consisting of L1 metric and multi-scale structural similarity (MSSSIM) metric to learn the network parameters. Different than the conventional MSE (mean squared error) metric, the perceptual metric coincides well with perceptual characteristics of the human visual system. Under the guidance of the perceptual metric, the RSA units are capable of predicting the visually sensitive areas at different scales. The proposed network can thus pay more attention to these areas for preserving visual informative structures at multiple scales. The experimental results on the Set5 and Set14 image set demonstrate that the combination of Perceptual metric and RSA units can significantly improve the reconstruction quality. In terms of PSNR and structural similarity (SSIM) values, the proposed method achieves better reconstruction results than the related works, and it is even comparable to some pre-trained networks. View Full-Text
Keywords: super-resolution; generator network; residual attention; perceptual metric super-resolution; generator network; residual attention; perceptual metric
Show Figures

Figure 1

MDPI and ACS Style

Sun, Y.; Shi, Y.; Yang, Y.; Zhou, W. Perceptual Metric Guided Deep Attention Network for Single Image Super-Resolution. Electronics 2020, 9, 1145.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop