RGB-D Object-to-CAD Retrieval
Loading...
Date
2018
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
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.
Description
@inproceedings{10.2312:3dor.20181052,
booktitle = {Eurographics Workshop on 3D Object Retrieval},
editor = {Telea, Alex and Theoharis, Theoharis and Veltkamp, Remco},
title = {{RGB-D Object-to-CAD Retrieval}},
author = {Pham, Quang-Hieu and Tran, Minh-Khoi and Do, Trong-Le and Ninh, Tu V. and Le, Tu-Khiem and Dao, Anh-Vu and Nguyen, Vinh-Tiep and Do, Minh N. and Duong, Anh-Duc and Hua, Binh-Son and Yu, Lap-Fai and Nguyen, Duc Thanh and Li, Wenhui and Yeung, Sai-Kit and Xiang, Shu and Zhou, Heyu and Nie, Weizhi and Liu, Anan and Su, Yuting and Tran, Minh-Triet and Bui, Ngoc-Minh},
year = {2018},
publisher = {The Eurographics Association},
ISSN = {1997-0471},
ISBN = {978-3-03868-053-6},
DOI = {10.2312/3dor.20181052}
}