Learning Spectral and Spatial Features Based on Generative Adversarial Network for Hyperspectral Image Super-Resolution
| Title | Learning Spectral and Spatial Features Based on Generative Adversarial Network for Hyperspectral Image Super-Resolution |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Jiang, Ruituo, Li, Xu, Gao, Ang, Li, Lixin, Meng, Hongying, Yue, Shigang, Zhang, Lei |
| Conference Name | IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium |
| Date Published | jul |
| Keywords | adversarial loss, Generative Adversarial Learning, generative adversarial network, generative adversarial networks, Generators, geophysical image processing, HSIs spatial SR, HSIs super-resolution, HSRGAN, hyperspectral image super-resolution, hyperspectral imagery, Hyperspectral images, Hyperspectral imaging, image enhancement, Image resolution, image texture, learning (artificial intelligence), loss function, Metrics, original HSIs, pixel-wise loss, pubcrawl, remote sensing, remote sensing applications, residual network, resilience, Resiliency, Scalability, spatial blocks, spatial features, Spatial resolution, spectral features, Super-resolution, super-resolved results |
| Abstract | Super-resolution (SR) of hyperspectral images (HSIs) aims to enhance the spatial/spectral resolution of hyperspectral imagery and the super-resolved results will benefit many remote sensing applications. A generative adversarial network for HSIs super-resolution (HSRGAN) is proposed in this paper. Specifically, HSRGAN constructs spectral and spatial blocks with residual network in generator to effectively learn spectral and spatial features from HSIs. Furthermore, a new loss function which combines the pixel-wise loss and adversarial loss together is designed to guide the generator to recover images approximating the original HSIs and with finer texture details. Quantitative and qualitative results demonstrate that the proposed HSRGAN is superior to the state of the art methods like SRCNN and SRGAN for HSIs spatial SR. |
| URL | https://ieeexplore.ieee.org/document/8900228/ |
| DOI | 10.1109/IGARSS.2019.8900228 |
| Citation Key | jiang_learning_2019 |
- Resiliency
- Metrics
- original HSIs
- pixel-wise loss
- pubcrawl
- remote sensing
- remote sensing applications
- residual network
- resilience
- loss function
- Scalability
- spatial blocks
- spatial features
- Spatial resolution
- spectral features
- Super-resolution
- super-resolved results
- hyperspectral image super-resolution
- Generative Adversarial Learning
- generative adversarial network
- generative adversarial networks
- Generators
- geophysical image processing
- HSIs spatial SR
- HSIs super-resolution
- HSRGAN
- adversarial loss
- hyperspectral imagery
- Hyperspectral images
- Hyperspectral imaging
- image enhancement
- Image resolution
- image texture
- learning (artificial intelligence)