Back to Search
Start Over
Spectral-Spatial MLP Network for Hyperspectral Image Super-Resolution
- Source :
- Remote Sensing; Volume 15; Issue 12; Pages: 3066
- Publication Year :
- 2023
- Publisher :
- Multidisciplinary Digital Publishing Institute, 2023.
-
Abstract
- Many hyperspectral image (HSI) super-resolution (SR) methods have been proposed and have achieved good results; however, they do not sufficiently preserve the spectral information. It is beneficial to sufficiently utilize the spectral correlation. In addition, most works super-resolve hyperspectral images using high computation complexity. To solve the above problems, a novel method based on a channel multilayer perceptron (CMLP) is presented in this article, which aims to obtain a better performance while reducing the computational cost. To sufficiently extract spectral features, a local-global spectral integration block is proposed, which consists of CMLP and some parameter-free operations. The block can extract local and global spectral features with low computational cost. In addition, a spatial feature group extraction block based on the CycleMLP framework is designed; it can extract local spatial features well and reduce the computation complexity and number of parameters. Extensive experiments demonstrate that our method achieves a good performance compared with other methods.
Details
- Language :
- English
- ISSN :
- 20724292
- Database :
- OpenAIRE
- Journal :
- Remote Sensing; Volume 15; Issue 12; Pages: 3066
- Accession number :
- edsair.multidiscipl..3051552aff1ad1e99f11682127502736
- Full Text :
- https://doi.org/10.3390/rs15123066