Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume 58, Issue 6, Pages 4304-4318Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2019.2962713
Keywords
Adversarial learning; band attention; hyperspectral image (HSI) super-resolution (SR)
Categories
Funding
- National Nature Science Foundation of China [61571345, 61671383, 91538101, 61501346, 61502367, 61901343]
- China Postdoctoral Science Foundation [2017M623124]
- China Postdoctoral Science Special Foundation [2018T111019]
- Open Research Fund of the CAS Key Laboratory of Spectral Imaging Technology [LSIT201924W]
- Fundamental Research Funds for the Central Universities [JB190107]
- 111 Project [B08038]
- Xidian University [10221150004]
Ask authors/readers for more resources
Hyperspectral image (HSI) super-resolution (SR) is a challenging task due to the problems of texture blur and spectral distortion when the upscaling factor is large. To meet these two challenges, band attention through the adversarial learning method is proposed in this article. First, we put the SR process in a generative adversarial network (GAN) framework, so that the resulted high-resolution HSI can keep more texture details. Second, different from the other band-by-band SR method, the input of our method is of full bands. In order to explore the correlation of spectral bands and avoid the spectral distortion, a band attention mechanism is proposed in our generative network. A series of spatial-spectral constraints or loss functions is imposed to guide the training of our generative network so as to further alleviate spectral distortion and texture blur. The experiments on the Pavia and Cave data sets demonstrate that the proposed GAN-based SR method can yield very highquality results, even under large upscaling factor (e.g., 8x). More importantly, it can outperform the other state-of-the-art methods by a margin which demonstrates its superiority and effectiveness.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available