VUE-net is a U-net inspired deep neural network for semantic segmentation of 3D point clouds of urban environment.
For this project the Semantic-KITTI dataset has been used.
All the details on how to run the code are contained in the python notebook file VUE-net.ipynb.
Results and architectural details can be viewed on the paper VUE-net.pdf.
The notebook is also accessible through Google Colab.