Intrinsic Images in the Wild

Information

• Paper topic: Image
• Software type: Code
• Able to run a replicability test: True
• Replicability score: 5
• License: MIT
• Build mechanism: Makefile
• Dependencies: python2.7/PIL==1.1.7/cython==0.19.2/numpy==1.8.0/scipy==0.13.2/scikit-image==0.9.3/scikit-learn==0.14.1
• Documentation score {0,1,2}: 1
• Reviewer: Julie Digne

Source code information

• Code URL: https://github.com/seanbell/intrinsic
• Git commit hash: 698b1e0fd23c216bb65164927c4de85b2c94b1af

Comments

Had to change a line in image_util.py to make it work with a more recent version of scikit-image: changed line 5 to "from skimage.restoration import denoise_bilateral". Adaptation in other context is easy: example of an integration is provided. All images in the dataset are provided with judgement files.

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