DeepCubeNetPublic

Reconstruction of compressively sensed hyperspectral images using deep learning.

DeepCubeNet is a deep learning architecture for reconstruction of compressively sensed hyperspectral images.

Usage: Install required libraries using pip install and the requirement file. Run predict.py to predict the test files in the input.

Other results can be found in our paper: D. Gedalin, Y. Oiknine, and A. Stern ' DeepCubeNet: Reconstruction of spectrally compressive sensed hyperspectral images with deep neural networks' , Optics Express, (2019)