Perception-driven semi-structured boundary vectorization

Information

• Paper topic: Images
• Software type: Binary
• Able to run a replicability test: True
• Replicability score: 5
• Software language: Cannot answer
• License: custom
• Build mechanism: None
• Dependencies:
• Documentation score {0,1,2}: 1
• Reviewer: Nicolas Bonneel <nicolas.bonneel@liris.cnrs.fr>
• Time spent for the test (build->first run, timeout at 100min): 20min

Source code information

• Code URL: http://www.cs.ubc.ca/labs/imager/tr/2018/PerceptionDrivenVectorization/executable.zip
• MD5 hash of the code archive: E3323994E24C0C70D3F9E8EDA5EE242C

Comments

The binary runs nicely. I could not find the examples shown in the paper for the multicolored examples, but some images are quite similar (e.g., a different penguin, a different red car, a different crown...) and produce reasonable results.
Note that the required numpy is version 1.16.1 and it doesn't work with 1.14.5 -- the python code is just the GUI.

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.