Improving 3D Point Cloud Reconstruction with Dynamic Tree-Structured Capsules

Abstract

When applying convolutional neural networks to 3D point cloud reconstruction, these do not seem to be able to learn meaningful 2D manifold embeddings, suffer a lack of explainability and are vulnerable to adversarial attacks [20]. Except for the latter, these shortcomings can be overcome with capsule networks. In this work we introduce an auto-encoder based on dynamic tree-structured capsule networks for sparse 3D point clouds with SDA-routing. Our approach preserves the spatial arrangements of the input data and increases the adversarial robustness without introducing additional computational overhead. Our experimental evaluation shows that our architecture outperforms the current state-of-the-art capsule and CNN-based networks.