In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data. 3D capsule networks arise as a direct consequence of our novel unified 3D auto-encoder formulation. Their dynamic routing scheme and the peculiar 2D latent space deployed by our approach bring in improvements for several common point cloud-related tasks, such as object classification, object reconstruction and part segmentation as substantiated by our extensive evaluations. Moreover, it enables new applications such as part interpolation and replacement.
- Pub Date:
- December 2018
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing
- As published in CVPR 2019 (camera ready version), with supplementary material