AaDR-PointCloud: An integrated point cloud processing network using attention and deep residual

Article type: Research Article

Authors: Li, Bo^a | Lu, TongWei^{b; *} | Min, Feng^b

Affiliations: [a] School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China | [b] Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology), China

Correspondence: [*] Corresponding author. TongWei Lu, School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China. E-mail: lutongwei@wit.edu.cn.

Abstract: 3D point cloud has irregularity and disorder, which pose challenges for point cloud analysis. In the past, the projection or point cloud voxelization methods often used were insufficient in accuracy and speed. In recent years, the methods using Transformer in the NLP field or ResNet in the deep learning field have shown promising results. This article expands these ideas and introduces a novel approach. This paper designs a model AaDR-PointCloud that combines self-attention blocks and deep residual point blocks and operates iteratively to extract point cloud information. The self-attention blocks used in the model are particularly suitable for point cloud processing because of their order independence. The deep residual point blocks used provide the expression of depth features. The model performs point cloud classification and segmentation tests on two shape classification datasets and an object part segmentation dataset, achieving higher accuracy on these benchmarks.

Keywords: PointCloud, transformer, ResNet, point cloud classification, point cloud part segmentation

DOI: 10.3233/JIFS-231997

Journal: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 3, pp. 6265-6277, 2024