Supplementary code to the paper O Sidorov, JY Hardeberg. Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution (Submitted to ICIP 2019).

The implementation is based on original Deep Image Prior code by Dmitry Ulyanov.

The framework was modified to process hyperspectral data using 2D or 3D convolutions:

• python = 3.6
• pytorch = 0.4
• numpy
• scipy
• matplotlib
• scikit-image
• jupyter

• Input and output hyperspectral data is contained in *.mat files.
• Specify a path to the file and name of the variable to read.
  For example, if data is contained in variable image:

  file_name  = 'data/inpainting/inpainting192.mat'
  mat = scipy.io.loadmat(file_name)
  img_np = mat["image"]
  

• Use custom code or one of the *.m files located at data/%task%/ to generate *.mat file.

• Follow one of the proposed notebook files to get the results.
  * 2D versions tend to demonstrate better accuracy.
• Try to modify parameters. Have fun.

Denoising:

Super-Resolution:

Inpainting: