A visual perception assistance network for semantic segmentation of 3D point clouds
Pytorch implementation of VPA-Net
Our environment: Umbuntu 20.04,CUDA 11.3
- Python 3.8
- pytorch >= 1.8
- torchsparse (install torchsparse uses the commands: sudo apt-get install libsparsehash-dev, pip install --upgrade git+https://github.com/mit-han-lab/[email protected])
- Other dependencies should be easily installed through pip or conda.
SemanticKITTI dataset can be found here. Download the files related to semantic segmentation and extract everything into the same folder.