Can I read Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Clouds on EtoBox?

Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Clouds by Floris, Alberto; Frittoli, Luca; Carrera, Diego; Boracchi, Giacomo is a scholarly article available to read on EtoBox.

What is Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Clouds about?

Deep neural networks require specific layers to process point clouds, as the scattered and irregular location of 3D points prevents the use of conventional convolutional filters. We introduce the composite layer, a flexible and general alternative to the existing convolutional operators that process 3D point clouds. We design our composite layer to extract and compress the spatial information from the 3D coordinates of points and then combine this with the feature vectors. Compared to mainstream point-convolutional layers such as ConvPoint and KPConv, our composite layer guarantees greater flexibility in network design and provides an additional form of regularization. To demonstrate the generality of our composite layers, we define both a convolutional composite layer and an aggregate version that combines spatial information and features in a nonlinear manner, and we use these layers to implement CompositeNets. Our experiments on synthetic and real-world datasets show that, in both classification, segmentation, and anomaly detection, our CompositeNets outperform ConvPoint, which uses the same sequential architecture, and achieve similar results as KPConv, which has a deeper, resi

Author

Floris, Alberto; Frittoli, Luca; Carrera, Diego; Boracchi, Giacomo

Published

2022

Language

EN