Skip to Main content Skip to Navigation
Journal articles

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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03169676
Contributor : Christine Grec Connect in order to contact the contributor
Submitted on : Monday, March 15, 2021 - 3:14:17 PM
Last modification on : Monday, December 13, 2021 - 9:17:15 AM
Long-term archiving on: : Wednesday, June 16, 2021 - 6:56:44 PM

File

DTIS21042.1615458520_preprint....
Files produced by the author(s)

Identifiers

Citation

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⟩

Share

Metrics

Les métriques sont temporairement indisponibles