Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor
This addresses noise and occlusion challenges in point cloud object classification for computer vision applications, representing an incremental improvement.
The paper tackled object classification in noisy 3D point clouds by proposing a noise-resistant point pair descriptor and a novel 4D convolutional neural network, achieving high retrieval accuracy as validated on three benchmark datasets.
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.