Deakin University
Browse

File(s) under permanent embargo

SHREC'18: RgB-D object-to-CAD retrieval

conference contribution
posted on 2018-01-01, 00:00 authored by Q H Pham, M K Tran, W Li, S Xiang, H Zhou, W Nie, A Liu, Y Su, M T Tran, N M Bui, T L Do, T V Ninh, T K Le, A V Dao, V T Nguyen, M N Do, A D Duong, B S Hua, L F Yu, Duc Thanh NguyenDuc Thanh Nguyen, S K Yeung
Recent advances in consumer-grade depth sensors have enable the collection of massive real-world 3D objects. Together with the rise of deep learning, it brings great potential for large-scale 3D object retrieval. In this challenge, we aim to study and evaluate the performance of 3D object retrieval algorithms with RGB-D data. To support the study, we expanded the previous ObjectNN dataset [HTT ∗ 17] to include RGB-D objects from both SceneNN [HPN ∗ 16] and ScanNet [DCS ∗ 17], with the CAD models from ShapeNetSem [CFG ∗ 15]. Evaluation results show that while the RGB-D to CAD retrieval problem is indeed challenging due to incomplete RGB-D reconstructions, it can be addressed to a certain extent using deep learning techniques trained on multi-view 2D images or 3D point clouds. The best method in this track has a 82% retrieval accuracy.

History

Event

Eurographics Association. Workshop (11th : 2018 : Delft, The Netherlands)

Series

Eurographics Association Workshop

Pagination

45 - 52

Publisher

Eurographics Association

Location

Delft, The Netherlands

Place of publication

Aire-la-Ville, Switzerland

Start date

2018-04-16

End date

2018-04-16

ISSN

1997-0463

eISSN

1997-0471

ISBN-13

9783038680536

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2018, Eurographics Association

Editor/Contributor(s)

[Unknown]

Title of proceedings

3DOR: Proceedings of the 11th Eurographics Workshop on 3D Object Retrieval 2018

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC