Skip to main content

ORIGINAL RESEARCH article

Front. Neurorobot.
Volume 18 - 2024 | doi: 10.3389/fnbot.2024.1436052

The Super-Resolution Reconstruction Algorithm of Multi-Scale Dilated Convolution Residual Network

Provisionally accepted
Shanqin Wang Shanqin Wang 1*Miao Zhang Miao Zhang 1Mengjun Miao Mengjun Miao 1,2
  • 1 Chuzhou Polytechnic, Chuzhou, China
  • 2 Qinghai Normal University, Xining, Qinghai Province, China

The final, formatted version of the article will be published soon.

    Aiming at the problems of traditional image super-resolution reconstruction algorithms in the image reconstruction process, such as small receptive field, insufficient multiscale feature extraction, and easy loss of image feature information, a super-resolution reconstruction algorithm of multi-scale dilated convolution network based on dilated convolution is proposed in this paper. First, the algorithm extracts features from the same input image through the dilated convolution kernels of different receptive fields to obtain feature maps with different scales; then, through the residual attention dense block, further obtain the features of the original low resolution images, local residual connections are added to fuse multi-scale feature information between multiple channels, and residual nested networks and jump connections are used at the same time to speed up deep network convergence and avoid network degradation problems. Finally, deep network extraction features, and it is fused with input features to increase the nonlinear expression ability of the network to enhance the super-resolution reconstruction effect. Experimental results show that compared with Bicubic, SRCNN, ESPCN, VDSR, DRCN, LapSRN, MemNet and DSRNet algorithms on the Set5, Set14, BSDS100 and Urban100 test sets, the proposed algorithm has improved peak signal-to-noise ratio and structural similarity, and reconstructed images .The visual effect is better.

    Keywords: Super-resolution reconstruction, Convolutional Neural Network, Dilated Convolution, Multi-level features, Residual dense block, Attention channel

    Received: 21 May 2024; Accepted: 29 Jul 2024.

    Copyright: © 2024 Wang, Zhang and Miao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Shanqin Wang, Chuzhou Polytechnic, Chuzhou, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.