ABD-Net: Attention Based Decomposition Network for 3D Point Cloud Decomposition

TL;DR

ABD-Net introduces an attention-based approach for decomposing 3D point clouds into basic geometric shapes, improving feature extraction and classification accuracy in 3D object recognition tasks.

Contribution

The paper presents ABD-Net, a novel neural network that combines local geometric encoding with attention mechanisms for effective 3D point cloud decomposition.

Findings

Enhanced 3D object classification accuracy on ModelNet40

Effective decomposition of point clouds into primitive shapes

Outperforms existing state-of-the-art methods

Abstract

In this paper, we propose Attention Based Decomposition Network (ABD-Net), for point cloud decomposition into basic geometric shapes namely, plane, sphere, cone and cylinder. We show improved performance of 3D object classification using attention features based on primitive shapes in point clouds. Point clouds, being the simple and compact representation of 3D objects have gained increasing popularity. They demand robust methods for feature extraction due to unorderness in point sets. In ABD-Net the proposed Local Proximity Encapsulator captures the local geometric variations along with spatial encoding around each point from the input point sets. The encapsulated local features are further passed to proposed Attention Feature Encoder to learn basic shapes in point cloud. Attention Feature Encoder models geometric relationship between the neighborhoods of all the points resulting in capturing global point cloud information. We demonstrate the results of our proposed ABD-Net on ANSI mechanical component and ModelNet40 datasets. We also demonstrate the effectiveness of ABD-Net over the acquired attention features by improving the performance of 3D object classification on ModelNet40 benchmark dataset and compare them with state-of-the-art techniques.