Abstract
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 uni-
fied formulation of the common 3D auto-encoders. The dynamic routing scheme [30] and the peculiar 2D latent space
deployed by our capsule networks 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.