VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation

TL;DR

This paper introduces VV-Net, a novel point cloud segmentation method that combines voxel-based encoding with a variational autoencoder and group equivariant CNNs, resulting in improved robustness and accuracy.

Contribution

The paper proposes a new voxel-based VAE architecture with RBF for local geometry and integrates group equivariant CNNs to enhance segmentation performance.

Findings

Outperforms state-of-the-art on ShapeNet and S3DIS datasets

Robust to noisy point cloud data

Efficiently captures local geometry within voxels

Abstract

We present a novel algorithm for point cloud segmentation. Our approach transforms unstructured point clouds into regular voxel grids, and further uses a kernel-based interpolated variational autoencoder (VAE) architecture to encode the local geometry within each voxel. Traditionally, the voxel representation only comprises Boolean occupancy information which fails to capture the sparsely distributed points within voxels in a compact manner. In order to handle sparse distributions of points, we further employ radial basis functions (RBF) to compute a local, continuous representation within each voxel. Our approach results in a good volumetric representation that effectively tackles noisy point cloud datasets and is more robust for learning. Moreover, we further introduce group equivariant CNN to 3D, by defining the convolution operator on a symmetry group acting on $\mathbb{Z}^3$ and its isomorphic sets. This improves the expressive capacity without increasing parameters, leading to more robust segmentation results. We highlight the performance on standard benchmarks and show that our approach outperforms state-of-the-art segmentation algorithms on the ShapeNet and S3DIS datasets.