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

doi:10.1109/ACCESS.2019.2929223

Return

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

2019-01-01

Kwok-Wai Hung

Zhikai Zhang

Jianmin Jiang *

DOI：10.1109/ACCESS.2019.2929223

Original

Save

View PDF

Abstract

En 中文

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.

Keywords:

Super-resolution

depthwise separable convolution

super-sampling

recursive convolution

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.