Shape-Oriented Convolution Neural Network for Point Cloud Analysis
This work addresses the challenge of analyzing 3D point clouds for applications like computer vision and robotics, presenting a novel method that improves performance in specific tasks.
The authors tackled the problem of learning shape features from irregular point clouds for 3D object analysis by proposing ShapeConv, a shape-oriented message passing scheme, and SOCNN, a hierarchical architecture, achieving state-of-the-art results in classification and part segmentation tasks.
Point cloud is a principal data structure adopted for 3D geometric information encoding. Unlike other conventional visual data, such as images and videos, these irregular points describe the complex shape features of 3D objects, which makes shape feature learning an essential component of point cloud analysis. To this end, a shape-oriented message passing scheme dubbed ShapeConv is proposed to focus on the representation learning of the underlying shape formed by each local neighboring point. Despite this intra-shape relationship learning, ShapeConv is also designed to incorporate the contextual effects from the inter-shape relationship through capturing the long-ranged dependencies between local underlying shapes. This shape-oriented operator is stacked into our hierarchical learning architecture, namely Shape-Oriented Convolutional Neural Network (SOCNN), developed for point cloud analysis. Extensive experiments have been performed to evaluate its significance in the tasks of point cloud classification and part segmentation.