SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset

Binh Son Hua, Quang Trung Truong, Minh Khoi Tran, Quang Hieu Pham, Asako Kanezaki, Tang Lee, Hung Yueh Chiang, Winston Hsu, Bo Li, Yijuan Lu, Henry Johan, Shoki Tashiro, Masaki Aono, Minh Triet Tran, Viet Khoi Pham, Hai Dang Nguyen, Vinh Tiep Nguyen, Quang Thang Tran, Thuyen V. Phan, Bao TruongMinh N. Do, Anh Duc Duong, Lap Fai Yu, Duc Thanh Nguyen, Sai Kit Yeung

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The 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 [HPN16] and CAD models from ShapeNet [CFG15]. 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.

Original languageEnglish (US)
Title of host publicationEG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval
EditorsIoannis Pratikakis, Maks Ovsjanikov, Florent Dupont
PublisherEurographics Association
Number of pages8
ISBN (Electronic)9783038680307
StatePublished - 2017
Event10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017 - Lyon, France
Duration: Apr 23 2017Apr 24 2017

Publication series

NameEurographics Workshop on 3D Object Retrieval, EG 3DOR
ISSN (Print)1997-0463
ISSN (Electronic)1997-0471


Conference10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction


Dive into the research topics of 'SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset'. Together they form a unique fingerprint.

Cite this