ConvPoint: Continuous convolutions for point cloud processing - Archive ouverte HAL Access content directly
Journal Articles Computers & Graphics: X Year : 2020

ConvPoint: Continuous convolutions for point cloud processing

Abstract

Point clouds are unstructured and unordered data, as opposed to images. Thus, most machine learning approach developed for image cannot be directly transferred to point clouds. In this paper, we propose a generalization of discrete convolutional neural networks (CNNs) in order to deal with point clouds by replacing discrete kernels by continuous ones. This formulation is simple, allows arbitrary point cloud sizes and can easily be used for designing neural networks similarly to 2D CNNs. We present experimental results with various architectures, highlighting the flexibility of the proposed approach. We obtain competitive results compared to the state-of-the-art on shape classification, part segmentation and semantic segmentation for large-scale point clouds.
Fichier principal
Vignette du fichier
DTIS21042.1615458520_preprint.pdf (3.04 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03169676 , version 1 (15-03-2021)

Identifiers

Cite

Alexandre Boulch. ConvPoint: Continuous convolutions for point cloud processing. Computers & Graphics: X, 2020, 88, pp.24-34. ⟨10.1016/j.cag.2020.02.005⟩. ⟨hal-03169676⟩
56 View
179 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More