Efficient Learning on Point Clouds with Basis Point Sets

2019-12-23

Basis Point Set (BPS) is a simple and efficient method for encoding 3D point clouds into fixed-length representations. It is based on a simple idea: select k fixed points in space and compute vectors from these basis points to the nearest points in a point cloud; use these vectors (or simply their norms) as features. The basis points are kept fixed for all the point clouds in the dataset, providing a fixed representation of every point cloud as a vector. This representation can then be used as input to arbitrary machine learning methods, in particular it can be used as input to off-the-shelf neural networks.

Basis Point Set (BPS) is a simple and efficient method for encoding 3D point clouds into fixed-length representations.

It is based on a simple idea: select k fixed points in space and compute vectors from these basis points to the nearest points in a point cloud; use these vectors (or simply their norms) as features. The basis points are kept fixed for all the point clouds in the dataset, providing a fixed representation of every point cloud as a vector.

This representation can then be used as input to arbitrary machine learning methods, in particular it can be used as input to off-the-shelf neural networks.

Below are the key differences between standard occupancy voxels, TSDF and the proposed BPS representation:

• continuous global vectors instead of simple binary flags or local distances in the cells;
• smaller number of cells required to represent shape accurately;
• BPS cell arrangement could be different from a standard rectangular grid, allowing different types of convolutions;
• significant improvement in performance: simply substituting occupancy voxels with BPS directional vectors results in a +9% accuracy improvement of a VoxNet-like 3D-convolutional network on a ModelNet40 classification challenge.

Check our ICCV 2019 paper and corresponding GitHub repository for more details.