File(s) under permanent embargo
SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset
conference contribution
posted on 2017-01-01, 00:00 authored by B S Hua, Q T Truong, M K Tran, Q H Pham, A Kanezaki, T Lee, H Y Chiang, W Hsu, B Li, Y Lu, H Johan, S Tashiro, M Aono, M T Tran, V K Pham, H D Nguyen, V T Nguyen, Q T Tran, T V Phan, B Truong, M N Do, A D Duong, L F Yu, Duc Thanh NguyenDuc Thanh Nguyen, S K YeungThe goal of this track is to study and evaluate the performance of 3D object retrieval algorithms using RGB-D data. This is inspired from the practical need to pair an object acquired from a consumer-grade depth camera to CAD models available in public datasets on the Internet. To support the study, we propose ObjectNN, a new dataset with well segmented and annotated RGB-D objects from SceneNN [HPN ∗ 16] and CAD models from ShapeNet [CFG ∗ 15]. The evaluation results show that the RGB-D to CAD retrieval problem, while being challenging to solve due to partial and noisy 3D reconstruction, can be addressed to a good extent using deep learning techniques, particularly, convolutional neural networks trained by multi-view and 3D geometry. The best method in this track scores 82% in accuracy.
History
Event
Eurographics Association. Workshop (2017 : Lyon, France)Series
Eurographics Association WorkshopPagination
25 - 32Publisher
Eurographics AssociationLocation
Lyon, FrancePlace of publication
Geneve, SwitzerlandPublisher DOI
Start date
2017-04-23End date
2017-04-24ISSN
1997-0463eISSN
1997-0471ISBN-13
9783038680307Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2017, The Eurographics AssociationEditor/Contributor(s)
I Pratikakis, F Dupont, M OvsjanikovTitle of proceedings
3DOR 17 : Proceedings of the 2017 Eurographics Workshop on 3D Object RetrievalUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC