VoxelNet_PyTorch

Pytorch based implementation of VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (https://arxiv.org/abs/1711.06396)

Architecture

Dependencies

• python3.5+
• PyTorch 1.4.0
• OpenCV
• Numpy

Note

Repo under active development. Will be updated with more files and instructions.

Data Preparation

└── DATA_DIR
       ├── training   <-- training data
       |   ├── image_2
       |   ├── label_2
       |   └── velodyne
       └── validation  <--- evaluation data
       |   ├── image_2
       |   ├── label_2
       |   └── velodyne

ToDo

[ ] Upload train files and results
[ ] Upload pre-trained model
[ ] Clean up code