Image Super-Resolution Using Lightweight Multiscale Residual Dense Network
The current super-resolution methods cannot fully exploit the global and local information of the original low-resolution image, resulting in loss of some information. In order to solve the problem, we propose a multiscale residual dense network (MRDN) for image super-resolution. This network is con...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | International Journal of Optics |
| Online Access: | http://dx.doi.org/10.1155/2020/2852865 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554560877494272 |
|---|---|
| author | Shilin Li Ming Zhao Zhengyun Fang Yafei Zhang Hongjie Li |
| author_facet | Shilin Li Ming Zhao Zhengyun Fang Yafei Zhang Hongjie Li |
| author_sort | Shilin Li |
| collection | DOAJ |
| description | The current super-resolution methods cannot fully exploit the global and local information of the original low-resolution image, resulting in loss of some information. In order to solve the problem, we propose a multiscale residual dense network (MRDN) for image super-resolution. This network is constructed based on the residual dense network. It can integrate the multiscale information of the image and avoid losing too much information in the deep level of the network, while extracting more information under different receptive fields. In addition, in order to reduce the redundancy of the network parameters of MRDN, we further develop a lightweight parameter method and deploy it at different scales. This method can not only reduce the redundancy of network parameters but also enhance the nonlinear mapping ability of the network at different scales. Thus, it can better learn and fit the feature information of the original image and recover the satisfactory super-resolution image. Extensive experiments are conducted, which demonstrate the effectiveness of the proposed method. |
| format | Article |
| id | doaj-art-43ea8d84bbf14a11b5bfa6684565bb0f |
| institution | Kabale University |
| issn | 1687-9384 1687-9392 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Optics |
| spelling | doaj-art-43ea8d84bbf14a11b5bfa6684565bb0f2025-02-03T05:51:15ZengWileyInternational Journal of Optics1687-93841687-93922020-01-01202010.1155/2020/28528652852865Image Super-Resolution Using Lightweight Multiscale Residual Dense NetworkShilin Li0Ming Zhao1Zhengyun Fang2Yafei Zhang3Hongjie Li4Eleictric Power Reasearch Institute of Yunnan Power Grid Co., Ltd., Kunming 650217, ChinaEleictric Power Reasearch Institute of Yunnan Power Grid Co., Ltd., Kunming 650217, ChinaCollege of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaCollege of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaEleictric Power Reasearch Institute of Yunnan Power Grid Co., Ltd., Kunming 650217, ChinaThe current super-resolution methods cannot fully exploit the global and local information of the original low-resolution image, resulting in loss of some information. In order to solve the problem, we propose a multiscale residual dense network (MRDN) for image super-resolution. This network is constructed based on the residual dense network. It can integrate the multiscale information of the image and avoid losing too much information in the deep level of the network, while extracting more information under different receptive fields. In addition, in order to reduce the redundancy of the network parameters of MRDN, we further develop a lightweight parameter method and deploy it at different scales. This method can not only reduce the redundancy of network parameters but also enhance the nonlinear mapping ability of the network at different scales. Thus, it can better learn and fit the feature information of the original image and recover the satisfactory super-resolution image. Extensive experiments are conducted, which demonstrate the effectiveness of the proposed method.http://dx.doi.org/10.1155/2020/2852865 |
| spellingShingle | Shilin Li Ming Zhao Zhengyun Fang Yafei Zhang Hongjie Li Image Super-Resolution Using Lightweight Multiscale Residual Dense Network International Journal of Optics |
| title | Image Super-Resolution Using Lightweight Multiscale Residual Dense Network |
| title_full | Image Super-Resolution Using Lightweight Multiscale Residual Dense Network |
| title_fullStr | Image Super-Resolution Using Lightweight Multiscale Residual Dense Network |
| title_full_unstemmed | Image Super-Resolution Using Lightweight Multiscale Residual Dense Network |
| title_short | Image Super-Resolution Using Lightweight Multiscale Residual Dense Network |
| title_sort | image super resolution using lightweight multiscale residual dense network |
| url | http://dx.doi.org/10.1155/2020/2852865 |
| work_keys_str_mv | AT shilinli imagesuperresolutionusinglightweightmultiscaleresidualdensenetwork AT mingzhao imagesuperresolutionusinglightweightmultiscaleresidualdensenetwork AT zhengyunfang imagesuperresolutionusinglightweightmultiscaleresidualdensenetwork AT yafeizhang imagesuperresolutionusinglightweightmultiscaleresidualdensenetwork AT hongjieli imagesuperresolutionusinglightweightmultiscaleresidualdensenetwork |