Deep Hybrid 2-D-3-D CNN Based on Dual Second-Order Attention With Camera Spectral Sensitivity Prior for Spectral Super-Resolution
- Ubuntu 16
- Pytorch 1.6.0
- Python 3.6
- opencv-python
- Models and datasets are available at the Baidu Yun(Password:2022).
- 'python eval.py' for the reconstructed hyperspectral results.
- 'python evaluation.py' for the MRAE and RMSE scores.
-
If the the work or the code is helpful, please cite the paper:
@article{li2021deep,
title={Deep hybrid 2-d-3-d CNN based on dual second-order attention with camera spectral sensitivity prior for spectral super-resolution}, author={Li, Jiaojiao and Wu, Chaoxiong and Song, Rui and Li, Yunsong and Xie, Weiying and He, Lihuo and Gao, Xinbo},
journal={IEEE Transactions on Neural Networks and Learning Systems},
year={2021},
publisher={IEEE}
}