SHREC'17: RgB-D to CAD Retrieval With ObjectNN Dataset
Document Type
Conference Proceeding
Publication Date
1-1-2017
School
Computing Sciences and Computer Engineering
Abstract
© 2017 The Eurographics Association. 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 [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.
Publication Title
Eurographics Workshop on 3D Object Retrieval, EG 3DOR
Volume
2017-April
First Page
25
Last Page
32
Recommended Citation
Hua, B.,
Truong, Q.,
Tran, M.,
Pham, Q.,
Kanezaki, A.,
Lee, T.,
Chiang, H.,
Hsu, W.,
Li, B.,
Lu, Y.,
Johan, H.,
Tashiro, S.,
Aono, M.,
Tran, M.,
Pham, V.,
Nguyen, H.,
Nguyen, V.,
Tran, Q.,
Phan, T.,
Truong, B.,
Do, M.,
Duong, A.,
Yu, L.,
Nguyen, D.,
Yeung, S.
(2017). SHREC'17: RgB-D to CAD Retrieval With ObjectNN Dataset. Eurographics Workshop on 3D Object Retrieval, EG 3DOR, 2017-April, 25-32.
Available at: https://aquila.usm.edu/fac_pubs/18389