Multistage reaction‐diffusion equation network for image super‐resolution
Abstract Deep learning‐based models have progressed considerably in single‐image super‐resolution. A high‐resolution pattern generation task is performed at the end of convolution neural networks (CNNs) with some convolution‐based operations in these models. However, this process may be difficult be...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-10-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12279 |
| _version_ | 1828304946344230912 |
|---|---|
| author | Xiaofeng Pu Zengmao Wang |
| author_facet | Xiaofeng Pu Zengmao Wang |
| author_sort | Xiaofeng Pu |
| collection | DOAJ |
| description | Abstract Deep learning‐based models have progressed considerably in single‐image super‐resolution. A high‐resolution pattern generation task is performed at the end of convolution neural networks (CNNs) with some convolution‐based operations in these models. However, this process may be difficult because all the work is done through the remarkable learning ability of CNN without any specific learning target. Reaction‐diffusion equation (RDE) is a mechanism involved in the pattern generation process that can serve as a guide for super‐resolution. It is proposed to embed RDE into a super‐resolution network by designing a reaction‐diffusion process block (RDPB) in this study. The proposed RDPB uses Euler method for iteratively solving one particular RDE, which is determined by the parameter generated through CNN. Accordingly, this module guides and leads the CNN in generating patterns for image super‐resolution. Moreover, a multistage framework is constructed to guide each network module further. On the basis of these two designs, the multistage reaction‐diffusion equation network is proposed for image super‐resolution. Experimental results demonstrated that the proposed model can obtain findings consistent with the conclusions of state‐of‐the‐art methods with a relatively shallow structure and small model size. |
| first_indexed | 2024-04-13T14:21:15Z |
| format | Article |
| id | doaj.art-cc0da488608c40359447ff73dade2fdb |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-13T14:21:15Z |
| publishDate | 2021-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-cc0da488608c40359447ff73dade2fdb2022-12-22T02:43:29ZengWileyIET Image Processing1751-96591751-96672021-10-0115122926293610.1049/ipr2.12279Multistage reaction‐diffusion equation network for image super‐resolutionXiaofeng Pu0Zengmao Wang1School of Computer Science Wuhan University Wuhan ChinaSchool of Computer Science Wuhan University Wuhan ChinaAbstract Deep learning‐based models have progressed considerably in single‐image super‐resolution. A high‐resolution pattern generation task is performed at the end of convolution neural networks (CNNs) with some convolution‐based operations in these models. However, this process may be difficult because all the work is done through the remarkable learning ability of CNN without any specific learning target. Reaction‐diffusion equation (RDE) is a mechanism involved in the pattern generation process that can serve as a guide for super‐resolution. It is proposed to embed RDE into a super‐resolution network by designing a reaction‐diffusion process block (RDPB) in this study. The proposed RDPB uses Euler method for iteratively solving one particular RDE, which is determined by the parameter generated through CNN. Accordingly, this module guides and leads the CNN in generating patterns for image super‐resolution. Moreover, a multistage framework is constructed to guide each network module further. On the basis of these two designs, the multistage reaction‐diffusion equation network is proposed for image super‐resolution. Experimental results demonstrated that the proposed model can obtain findings consistent with the conclusions of state‐of‐the‐art methods with a relatively shallow structure and small model size.https://doi.org/10.1049/ipr2.12279Optical, image and video signal processingComputer vision and image processing techniquesNeural nets |
| spellingShingle | Xiaofeng Pu Zengmao Wang Multistage reaction‐diffusion equation network for image super‐resolution IET Image Processing Optical, image and video signal processing Computer vision and image processing techniques Neural nets |
| title | Multistage reaction‐diffusion equation network for image super‐resolution |
| title_full | Multistage reaction‐diffusion equation network for image super‐resolution |
| title_fullStr | Multistage reaction‐diffusion equation network for image super‐resolution |
| title_full_unstemmed | Multistage reaction‐diffusion equation network for image super‐resolution |
| title_short | Multistage reaction‐diffusion equation network for image super‐resolution |
| title_sort | multistage reaction diffusion equation network for image super resolution |
| topic | Optical, image and video signal processing Computer vision and image processing techniques Neural nets |
| url | https://doi.org/10.1049/ipr2.12279 |
| work_keys_str_mv | AT xiaofengpu multistagereactiondiffusionequationnetworkforimagesuperresolution AT zengmaowang multistagereactiondiffusionequationnetworkforimagesuperresolution |