Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Multi-scale residual hierarchical dense networks for single image super-resolution

Liu, Chuangchuang, Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766, Chen, Changyou, Rosin, Paul ORCID: https://orcid.org/0000-0002-4965-3884, Yan, Yitong, Jin, Longcun and Pen, Xinyi 2019. Multi-scale residual hierarchical dense networks for single image super-resolution. IEEE Access 7 , 60572 -60583. 10.1109/ACCESS.2019.2915943

[thumbnail of 08712146.pdf]
Preview
PDF - Accepted Post-Print Version
Download (2MB) | Preview

Abstract

Single image super-resolution is known to be an ill-posed problem, which has been studied for decades. With the developments of deep convolutional neural networks, the CNN-based single image super-resolution methods have greatly improved the quality of the generated high-resolution images. However, it is difficult for image super-resolution to make full use of the relationship between pixels in low-resolution images. To address this issue, we propose a novel multi-scale residual hierarchical dense network, which tries to find the dependencies in multi-level and multi-scale features. Specially, we apply the atrous spatial pyramid pooling, which concatenates multiple atrous convolutions with different dilation rates, and design a residual hierarchical dense structure for single image super-resolution. The atrous-spatial pyramid-pooling module is used for learning the relationship of features at multiple scales; while the residual hierarchical dense structure, which consists of several hierarchical dense blocks with skip connections, aims to adaptively detect key information from multi-level features. Meanwhile, dense features from different groups are connected in a dense approach by hierarchical dense blocks, which can adequately extract local multi-level features. Extensive experiments on benchmark datasets illustrate the superiority of our proposed method compared with state-of-the-art methods. The super-resolution results on benchmark datasets of our method can be downloaded from https://github.com/Rainyfish/MS-RHDN, and the source code will be released upon acceptance of the paper.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 2169-3536
Date of First Compliant Deposit: 15 May 2019
Date of Acceptance: 6 May 2019
Last Modified: 06 Nov 2023 18:45
URI: https://orca.cardiff.ac.uk/id/eprint/122393

Citation Data

Cited 19 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics