English

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

Computer Vision and Pattern Recognition 2018-04-09 v1 Artificial Intelligence Robotics

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.

Keywords

Cite

@article{arxiv.1804.02077,
  title  = {Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor},
  author = {Dmytro Bobkov and Sili Chen and Ruiqing Jian and Muhammad Iqbal and Eckehard Steinbach},
  journal= {arXiv preprint arXiv:1804.02077},
  year   = {2018}
}

Comments

8 pages

R2 v1 2026-06-23T01:15:33.151Z