Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor

TL;DR

This paper introduces a noise-resistant point pair descriptor combined with a 4D CNN for robust object classification in 3D point clouds, effectively handling noise, occlusion, and irregular sampling.

Contribution

The paper presents a novel point pair descriptor and a 4D convolutional layer that together improve object classification accuracy in noisy and occluded point cloud data.

Findings

Outperforms existing methods on benchmark datasets

Robust to noise and occlusion

Effective in irregular sampling conditions

Abstract

Object retrieval and classification in point cloud data is challenged by noise, irregular sampling density and occlusion. To address this issue, we propose a point pair descriptor that is robust to noise and occlusion and achieves high retrieval accuracy. We further show how the proposed descriptor can be used in a 4D convolutional neural network for the task of object classification. We propose a novel 4D convolutional layer that is able to learn class-specific clusters in the descriptor histograms. Finally, we provide experimental validation on 3 benchmark datasets, which confirms the superiority of the proposed approach.