Octree Guided CNN With Spherical Kernels for 3D Point Clouds

Research output: Chapter in Book/Conference paperConference paper

3 Citations (Scopus)

Abstract

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point clouds,and hierarchically coarsens the data representation with space partitioning. At the same time, the proposed spherical kernels systematically quantize point neighborhoods to identify local geometric structures in the data, while maintaining the properties of translation-invariance and asymmetry. We specify spherical kernels with the help of network neurons that in turn are associated with spatial locations.We exploit this association to avert dynamic kernel generation during network training that enables efficient learning with high resolution point clouds. The effectiveness of the proposed technique is established on the benchmark tasks of 3D object classification and segmentation, achieving competitive performance on ShapeNet and RueMonge2014 datasets.
Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages9623-9632
ISBN (Electronic)978-1-7281-3293-8
DOIs
Publication statusPublished - 9 Jan 2020
EventIEEE Conference on Computer Vision and Pattern Recognition 2019 - Long Beach Convention & Entertainment Center, Long Beach, United States
Duration: 16 Jun 201920 Jun 2019
http://cvpr2019.thecvf.com/

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition 2019
Abbreviated titleCVPR 2019
CountryUnited States
CityLong Beach
Period16/06/1920/06/19
Internet address

Fingerprint Dive into the research topics of 'Octree Guided CNN With Spherical Kernels for 3D Point Clouds'. Together they form a unique fingerprint.

  • Cite this

    Lei, H., Akhtar, N., & Mian, A. (2020). Octree Guided CNN With Spherical Kernels for 3D Point Clouds. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019) (pp. 9623-9632). [156730] USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPR.2019.00986