PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing
This work addresses computational bottlenecks in raw point cloud processing for applications like 3D object recognition and scene understanding, offering an incremental improvement over prior capsule network methods.
The authors tackled the computational inefficiency and inability to represent entire point clouds as single capsules in existing capsule networks by proposing PointCaps, a novel architecture with parameter sharing, Euclidean distance routing, and a class-independent latent representation, achieving better reconstruction with comparable classification and segmentation accuracy while significantly reducing parameters and FLOPs.
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.