Real-Time Image Super-Resolution Using Recursive Depthwise Separable Convolution Network
Open Access
- 16 July 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 99804-99816
Abstract
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
Funding Information
- National Natural Science Foundation of China (61602312, 61620106008)
- Shenzhen Commission for Scientific Research and Innovations (JCYJ20160226191842793)
This publication has 24 references indexed in Scilit:
- Rethinking the Inception Architecture for Computer Vision2016
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Deep Networks for Image Super-Resolution with Sparse Prior2015
- Single-image super-resolution using iterative Wiener filter based on nonlocal meansSignal Processing: Image Communication, 2015
- Learning-based image interpolation via robust k-NN searching for coherent AR parameters estimationJournal of Visual Communication and Image Representation, 2015
- Fast and accurate image upscaling with super-resolution forests2015
- Fast image interpolation using the bilateral filterIET Image Processing, 2012
- Robust Soft-Decision Interpolation Using Weighted Least SquaresIEEE Transactions on Image Processing, 2011
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002