Meng, Hsien-Yu, Gao, Lin, Lai, Yukun  ORCID: https://orcid.org/0000-0002-2094-5680 and Manocha, Dinesh
2019.
VV-NET: Voxel VAE Net with group convolutions for point cloud segmentation.
Presented at: IEEE International Conference on Computer Vision (ICCV),
Seoul, Korea,
27 October - 2 November 2019.
10.1109/ICCV.2019.00859
|
Preview |
PDF
- Accepted Post-Print Version
Download (4MB) | Preview |
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 Z3 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.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Related URLs: | |
| Date of First Compliant Deposit: | 17 August 2019 |
| Date of Acceptance: | 22 July 2019 |
| Last Modified: | 26 Aug 2025 10:15 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/124986 |
Citation Data
Cited 100 times in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions