Intrinsic Images in the Wild

Information

• Paper topic: Images
• Software type: Code
• Able to run a replicability test: True
• Replicability score: 5
• Software language: Python
• 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 <julie.digne@liris.cnrs.fr>
• Time spent for the test (build->first run, timeout at 100min): 60min

Source code information

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

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.

If you want to contribute with another review, please follow these instructions.

Please consider to cut/paste/edit the raw JSON data attached to this paper.