IPC-Net: 3D point-cloud segmentation using deep inter-point convolutional layers

TL;DR

This paper introduces IPC-Net, a novel deep learning architecture for 3D point-cloud segmentation that outperforms existing models like PointNet by extracting more comprehensive features, especially benefiting complex geometries.

Contribution

The paper provides a detailed analysis of PointNet and proposes IPC-Net, a new architecture with inter-point activation layers that enhances feature extraction and segmentation accuracy.

Findings

IPC-Net outperforms PointNet on various 3D shape datasets.

Inter-point activation layers are crucial for accurate segmentation.

High generalization observed across diverse 3D geometries.

Abstract

Over the last decade, the demand for better segmentation and classification algorithms in 3D spaces has significantly grown due to the popularity of new 3D sensor technologies and advancements in the field of robotics. Point-clouds are one of the most popular representations to store a digital description of 3D shapes. However, point-clouds are stored in irregular and unordered structures, which limits the direct use of segmentation algorithms such as Convolutional Neural Networks. The objective of our work is twofold: First, we aim to provide a full analysis of the PointNet architecture to illustrate which features are being extracted from the point-clouds. Second, to propose a new network architecture called IPC-Net to improve the state-of-the-art point cloud architectures. We show that IPC-Net extracts a larger set of unique features allowing the model to produce more accurate segmentations compared to the PointNet architecture. In general, our approach outperforms PointNet on every family of 3D geometries on which the models were tested. A high generalisation improvement was observed on every 3D shape, especially on the rockets dataset. Our experiments demonstrate that our main contribution, inter-point activation on the network's layers, is essential to accurately segment 3D point-clouds.