This is an unofficial implementation of VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection in pytorch. A large part of this project is based on the work here

• python3.5
• pytorch (tested on 0.3.1)
• opencv
• shapely
• mayavi

1. Clone this repository.
2. Compile the Cython module for box_overlaps

$ python3 setup.py build_ext --inplace

3. Compile the nms model

$ python3 nms/build.py

1. Download the 3D KITTI detection dataset from here. Data to download include:

   • Velodyne point clouds (29 GB): input data to VoxelNet
   • Training labels of object data set (5 MB): input label to VoxelNet
   • Camera calibration matrices of object data set (16 MB): for visualization of predictions
   • Left color images of object data set (12 GB): for visualization of predictions

2. In this project, the cropped point cloud data for training and validation. Point clouds outside the image coordinates are removed.

$ python3 data/crop.py

3. Split the training set into training and validation set according to the protocol here.

└── DATA_DIR
       ├── training   <-- training data
       |   ├── image_2
       |   ├── label_2
       |   ├── velodyne
       |   └── crop
       └── testing  <--- testing data
       |   ├── image_2
       |   ├── label_2
       |   ├── velodyne
       |   └── crop

• training code
• data augmentation
• validation code
• reproduce results for Car, Pedestrian and Cyclist
• multi-gpu support
• improve the performances