Generalized Convolutional Neural Networks for Point Cloud Data
This addresses the need for efficient 3D data processing in computer vision, though it appears incremental as an adaptation of existing CNN concepts to point clouds.
The paper tackles the problem of applying convolutional neural networks directly to point cloud data, achieving a method that bypasses extensive feature engineering and is computationally efficient with few parameters.
The introduction of cheap RGB-D cameras, stereo cameras, and LIDAR devices has given the computer vision community 3D information that conventional RGB cameras cannot provide. This data is often stored as a point cloud. In this paper, we present a novel method to apply the concept of convolutional neural networks to this type of data. By creating a mapping of nearest neighbors in a dataset, and individually applying weights to spatial relationships between points, we achieve an architecture that works directly with point clouds, but closely resembles a convolutional neural net in both design and behavior. Such a method bypasses the need for extensive feature engineering, while proving to be computationally efficient and requiring few parameters.