Monocular Image Based 3D Model Retrieval

Li, Wenhui; Liu, Anan; Nie, Weizhi; Song, Dan; Li, Yuqian; Wang, Weijie; Xiang, Shu; Zhou, Heyu; Bui, Ngoc-Minh; Cen, Yunchi; Chen, Zenian; Chung-Nguyen, Huy-Hoang; Diep, Gia-Han; Do, Trong-Le; Doubrovski, Eugeni L.; Duong, Anh-Duc; Geraedts, Jo M. P.; Guo, Haobin; Hoang, Trung-Hieu; Li, Yichen; Liu, Xing; Liu, Zishun; Luu, Duc-Tuan; Ma, Yunsheng; Nguyen, Vinh-Tiep; Nie, Jie; Ren, Tongwei; Tran, Mai-Khiem; Tran-Nguyen, Son-Thanh; Tran, Minh-Triet; Vu-Le, The-Anh; Wang, Charlie C. L.; Wang, Shijie; Wu, Gangshan; Yang, Caifei; Yuan, Meng; Zhai, Hao; Zhang, Ao; Zhang, Fan; Zhao, Sicheng

Monocular Image Based 3D Model Retrieval

Files

103-110.pdf (1.62 MB)

Date

2019

Publisher

The Eurographics Association

Abstract

Monocular image based 3D object retrieval is a novel and challenging research topic in the field of 3D object retrieval. Given a RGB image captured in real world, it aims to search for relevant 3D objects from a dataset. To advance this promising research, we organize this SHREC track and build the first monocular image based 3D object retrieval benchmark by collecting 2D images from ImageNet and 3D objects from popular 3D datasets such as NTU, PSB, ModelNet40 and ShapeNet. The benchmark contains classified 21,000 2D images and 7,690 3D objects of 21 categories. This track attracted 9 groups from 4 countries and the submission of 20 runs. To have a comprehensive comparison, 7 commonly-used retrieval performance metrics have been used to evaluate their retrieval performance. The evaluation results show that the supervised cross domain learning get the superior retrieval performance (Best NN is 97.4 %) by bridging the domain gap with label information. However, there is still a big challenge for unsupervised cross domain learning (Best NN is 61.2%), which is more practical for the real application. Although we provided both view images and OBJ file for each 3D model, all the participants use the view images to represent the 3D model. One of the interesting work in the future is directly using the 3D information and 2D RGB information to solve the task of monocular Image based 3D model retrieval.

        @inproceedings{10.2312:3dor.20191068
,
booktitle = {Eurographics Workshop on 3D Object Retrieval
},
editor = {Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
},
title = {{Monocular Image Based 3D Model Retrieval
}},
author = {Li, Wenhui and 
Liu, Anan and 
Chen, Zenian and 
Chung-Nguyen, Huy-Hoang and 
Diep, Gia-Han and 
Do, Trong-Le and 
Doubrovski, Eugeni L. and 
Duong, Anh-Duc and 
Geraedts, Jo M. P. and 
Guo, Haobin and 
Hoang, Trung-Hieu and 
Li, Yichen and 
Nie, Weizhi and 
Liu, Xing and 
Liu, Zishun and 
Luu, Duc-Tuan and 
Ma, Yunsheng and 
Nguyen, Vinh-Tiep and 
Nie, Jie and 
Ren, Tongwei and 
Tran, Mai-Khiem and 
Tran-Nguyen, Son-Thanh and 
Tran, Minh-Triet and 
Song, Dan and 
Vu-Le, The-Anh and 
Wang, Charlie C. L. and 
Wang, Shijie and 
Wu, Gangshan and 
Yang, Caifei and 
Yuan, Meng and 
Zhai, Hao and 
Zhang, Ao and 
Zhang, Fan and 
Zhao, Sicheng and 
Li, Yuqian and 
Wang, Weijie and 
Xiang, Shu and 
Zhou, Heyu and 
Bui, Ngoc-Minh and 
Cen, Yunchi
},
year = {2019
},
publisher = {The Eurographics Association
},
ISSN = {1997-0471
},
ISBN = {978-3-03868-077-2
},
DOI = {10.2312/3dor.20191068
}
}