Orienting point clouds with dipole propagation

Information

• Paper topic: Geometry
• Software type: Code
• Able to run a replicability test: True
• Replicability score: 5
• Paper listed in the Graphics Replicability Stamp Initiative
• Software language: python
• License: no
• Build mechanism: NA
• Dependencies: pytorch,pytorch-geometric,argparse,Open3D
• 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): 100min

Source code information

• Code URL: https://github.com/galmetzer/dipole-normal-prop
• Git commit hash: 0887b893b153f4ce6b09e4dd485f9b042f15b706
• Software Heritage link:

Comments

I installed python 3.6, pytorch1.8 and pytorch-geometric with anaconda (instructions similar to script install_cu102.sh).

Misc. comments

I was able to run the program on several models: lion, hand, fandisk.

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.