End-to-end Optimization of Optics and Image Processing for Achromatic Extended Depth of Field and Super-resolution Imaging

Information

• Paper topic: Image
• Software type: Code
• Able to run a replicability test: True
• Replicability score: 3
• License: unspecified
• Build mechanism: Not applicable (python, Matlab..)
• Dependencies: tensorflow-gpu / protobuf / poppy
• Documentation score {0,1,2}: 1
• Reviewer: Nicolas Mellado

Source code information

• Code URL: https://github.com/vsitzmann/deepoptics
• Git commit hash: 21c244dbadc9fb686d5f51a81c5b08a298b36c98
• Software Heritage link:

Comments

I had to patch the environment.yml file to use up-to-date pip packages.
I could train the network and see image results using tensorboard, however  it is not clear how this images should be compared with the results shown in the paper.

There are two options to add a review to this article:

• Open a pull request at https://github.com/dcoeurjo/ReplData-private
• Fill the form below (this option requires manual work and might be avoided if possible):
  TODO: ADD FORM