Deakin University
Browse
DOCUMENT
nguyen-revisitingpoint-2019.pdf (2.35 MB)
DOCUMENT
nguyen-revisitingpoint-evid-2019.pdf (126.46 kB)
DOCUMENT
nguyen-revisitingpoint-pre-2019.pdf (2.99 MB)
1/0
3 files

Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data

conference contribution
posted on 2019-01-01, 00:00 authored by Mikaela Angelina Uy, Quang-Hieu Pham, Binh-Son Hua, Duc Thanh NguyenDuc Thanh Nguyen, Sai-Kit Yeung
Deep learning techniques for point cloud data have demonstrated great potentials in solving classical problems in 3D computer vision such as 3D object classification and segmentation. Several recent 3D object classification methods have reported state-of-the-art performance on CAD model datasets such as ModelNet40 with high accuracy ( 92%). Despite such impressive results, in this paper, we argue that object classification is still a challenging task when objects are framed with real-world settings. To prove this, we introduce ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data. From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions. We identify three key open problems for point cloud object classification, and propose new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background. Our dataset and code are publicly available in our project page https://hkust-vgd.github.io/scanobjectnn/

History

Pagination

1588-1597

Location

Seoul, Korea

Open access

  • Yes

Start date

2019-10-27

End date

2019-11-02

Language

eng

Publication classification

E1 Full written paper - refereed

Title of proceedings

ICCV 2019 : Proceedings of the 2019 IEEE International Conference on Computer Vision

Event

IEEE International Conference on Computer Vision (2019 : Seoul, Korea)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC