Noise-Resistant Deep Learning for Object Classification in Three-Dimensional Point Clouds Using a Point Pair Descriptor

By Dmytro Bobkov, Sili Chen, Ruiqing Jian, Muhammad Zafar Iqbal, Eckehard G. Steinbach. 2018

21 citations recorded by the source corpus.

Object retrieval and classification in point cloud data are 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 four-dimensional (4-D) convolutional neural network for the task of object classification. We propose a novel 4-D convolutional layer that is able to learn class-specific clusters in the descriptor histograms. Finally, we provide experimental validation on three benchmark datasets, which confirms the superiority of the proposed approach.

Subfields: Aerospace Engineering, Computational Mechanics, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computational Mechanics

In Geology

Citations in the corpus

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data (2019, methodology): “Other works synthesize challenges on CAD data by introducing noise simulated by Gaussians [4, 12] or created with a parametic model [6] to mimic real world scenarios.”
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors (2018, methodology): “We now study 3 identical networks, trained for 3 different PPF formulations: ours, PPFH (the PPF used in FPFH [34]) and Bobkov1 et al. [6].”