PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing

TL;DR

PointCaps introduces a lightweight capsule network architecture with Euclidean distance routing for efficient and accurate raw point cloud processing, capturing spatial relationships and geometric features.

Contribution

It proposes a novel convolutional capsule architecture with parameter sharing and a Euclidean distance routing algorithm, improving efficiency and interpretability in point cloud analysis.

Findings

Lower parameter count and FLOPs compared to existing methods

Achieves better reconstruction quality

Maintains comparable classification and segmentation accuracy

Abstract

Raw point cloud processing using capsule networks is widely adopted in classification, reconstruction, and segmentation due to its ability to preserve spatial agreement of the input data. However, most of the existing capsule based network approaches are computationally heavy and fail at representing the entire point cloud as a single capsule. We address these limitations in existing capsule network based approaches by proposing PointCaps, a novel convolutional capsule architecture with parameter sharing. Along with PointCaps, we propose a novel Euclidean distance routing algorithm and a class-independent latent representation. The latent representation captures physically interpretable geometric parameters of the point cloud, with dynamic Euclidean routing, PointCaps well-represents the spatial (point-to-part) relationships of points. PointCaps has a significantly lower number of parameters and requires a significantly lower number of FLOPs while achieving better reconstruction with comparable classification and segmentation accuracy for raw point clouds compared to state-of-the-art capsule networks.