Real-Time Image Super-Resolution Using Recursive Depthwise Separable Convolution Network

In recent years, deep convolutional neural networks (CNNs) have been widely used for image super-resolution (SR) to achieve a range of sophisticated performances. Despite the significant advancement made in CNNs, it is still difficult to apply CNNs to practical SR applications due to enormous comput...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.99804-99816
Main Authors: Hung, Kwok-Wai, Zhang, Zhikai, Jiang, Jianmin
Format: Article
Language:English
Subjects:
Adaptation models
Adaptive sampling
Artificial neural networks
Complexity theory
Computational modeling
Convolution
depthwise separable convolution
Image resolution
Machine learning
Mathematical models
Multiplication
Neural networks
Parameters
Real time
Real-time systems
recursive convolution
Signal resolution
Super-resolution
super-sampling
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, deep convolutional neural networks (CNNs) have been widely used for image super-resolution (SR) to achieve a range of sophisticated performances. Despite the significant advancement made in CNNs, it is still difficult to apply CNNs to practical SR applications due to enormous computations of deep convolutions. In this paper, we propose two lightweight deep neural networks using depthwise separable convolution for the real-time image SR. Specifically, depthwise separable convolution divides the standard convolution into depthwise convolution and pointwise convolution to significantly reduce the number of model parameters and multiplication operations. Moreover, recursive learning is adopted to increase the depth and receptive field of the network in order to improve the SR quality without increasing the model parameters. Finally, we propose a novel technique called Super-Sampling (SS) to learn more abundant high-resolution information by over-sampling the output image followed by adaptive down-sampling. The proposed two models, named SSNet-M and SSNet, outperform the existing state-of-the-art real-time image SR networks, including SRCNN, FSRCNN, ESPCN, and VDSR, in terms of model complexity, and subjective and PSNR/SSIM evaluations on Set5, Set14, B100, Urban100, and Manga109.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2929223