Deep Residual Dense Network for Single Image Super-Resolution
In this paper, we propose a deep residual dense network (<i>DRDN</i>) for single image super- resolution. Based on human perceptual characteristics, the residual in residual dense block strategy (<i>RRDB</i>) is exploited to implement various depths in network architectures....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/5/555 |
| _version_ | 1797395107601711104 |
|---|---|
| author | Yogendra Rao Musunuri Oh-Seol Kwon |
| author_facet | Yogendra Rao Musunuri Oh-Seol Kwon |
| author_sort | Yogendra Rao Musunuri |
| collection | DOAJ |
| description | In this paper, we propose a deep residual dense network (<i>DRDN</i>) for single image super- resolution. Based on human perceptual characteristics, the residual in residual dense block strategy (<i>RRDB</i>) is exploited to implement various depths in network architectures. The proposed model exhibits a simple sequential structure comprising residual and dense blocks with skip connections. It improves the stability and computational complexity of the network, as well as the perceptual quality. We adopt a perceptual metric to learn and assess the quality of the reconstructed images. The proposed model is trained with the Diverse2k dataset, and the performance is evaluated using standard datasets. The experimental results confirm that the proposed model exhibits superior performance, with better reconstruction results and perceptual quality than conventional methods. |
| first_indexed | 2024-03-09T00:29:35Z |
| format | Article |
| id | doaj.art-89f2e67990fc4459b166c76be790a83c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T00:29:35Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-89f2e67990fc4459b166c76be790a83c2023-12-11T18:38:49ZengMDPI AGElectronics2079-92922021-02-0110555510.3390/electronics10050555Deep Residual Dense Network for Single Image Super-ResolutionYogendra Rao Musunuri0Oh-Seol Kwon1Department of Control & Instrumentation Engineering, Changwon National University, Changwon 51140, KoreaSchool of Electrical, Electronics & Control Instrumentation Eng., Changwon National University, Changwon 51140, KoreaIn this paper, we propose a deep residual dense network (<i>DRDN</i>) for single image super- resolution. Based on human perceptual characteristics, the residual in residual dense block strategy (<i>RRDB</i>) is exploited to implement various depths in network architectures. The proposed model exhibits a simple sequential structure comprising residual and dense blocks with skip connections. It improves the stability and computational complexity of the network, as well as the perceptual quality. We adopt a perceptual metric to learn and assess the quality of the reconstructed images. The proposed model is trained with the Diverse2k dataset, and the performance is evaluated using standard datasets. The experimental results confirm that the proposed model exhibits superior performance, with better reconstruction results and perceptual quality than conventional methods.https://www.mdpi.com/2079-9292/10/5/555super-resolutionperceptual<i>DRDN</i>residualdense blocks |
| spellingShingle | Yogendra Rao Musunuri Oh-Seol Kwon Deep Residual Dense Network for Single Image Super-Resolution Electronics super-resolution perceptual <i>DRDN</i> residual dense blocks |
| title | Deep Residual Dense Network for Single Image Super-Resolution |
| title_full | Deep Residual Dense Network for Single Image Super-Resolution |
| title_fullStr | Deep Residual Dense Network for Single Image Super-Resolution |
| title_full_unstemmed | Deep Residual Dense Network for Single Image Super-Resolution |
| title_short | Deep Residual Dense Network for Single Image Super-Resolution |
| title_sort | deep residual dense network for single image super resolution |
| topic | super-resolution perceptual <i>DRDN</i> residual dense blocks |
| url | https://www.mdpi.com/2079-9292/10/5/555 |
| work_keys_str_mv | AT yogendraraomusunuri deepresidualdensenetworkforsingleimagesuperresolution AT ohseolkwon deepresidualdensenetworkforsingleimagesuperresolution |