Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification

Convolution is an effective technique that can be used to obtain abstract feature representations using hierarchical layers in deep networks. However, performing convolution in non-Euclidean topological spaces such as the unit ball (B³) is still an under-explored problem. In this paper, we propose a light-weight experimental architecture for 3D object classification, that operates in B³. The proposed network utilizes both hand-crafted and learned features, and uses capsules in the penultimate layer to disentangle 3D shape features through pose and view equivariance. It simultaneously maintains an intrinsic co-ordinate frame, where mutual relationships between object parts are preserved. Furthermore, we show that the optimal view angles for extracting patterns from 3D objects depend on its shape and achieve compelling results with a relatively shallow network, compared to the state-of-the-art.