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 Truong; Minh N. Do; Anh Duc Duong; Lap Fai Yu; Duc Thanh Nguyen; Sai Kit Yeung

doi:10.2312/3dor.20171048

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 proceeding › Conference contribution

Abstract

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.

Original language	English (US)
Title of host publication	EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval
Editors	Ioannis Pratikakis, Maks Ovsjanikov, Florent Dupont
Publisher	Eurographics Association
Pages	25-32
Number of pages	8
ISBN (Electronic)	9783038680307
DOIs	https://doi.org/10.2312/3dor.20171048
State	Published - 2017
Event	10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017 - Lyon, France Duration: Apr 23 2017 → Apr 24 2017

Publication series

Name	Eurographics Workshop on 3D Object Retrieval, EG 3DOR
Volume	2017-April
ISSN (Print)	1997-0463
ISSN (Electronic)	1997-0471

Conference

Conference	10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017
Country	France
City	Lyon
Period	4/23/17 → 4/24/17

ASJC Scopus subject areas

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

Access to Document

10.2312/3dor.20171048

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

Cite this

Hua, B. S., Truong, Q. T., Tran, M. K., Pham, Q. H., Kanezaki, A., Lee, T., Chiang, H. Y., Hsu, W., Li, B., Lu, Y., Johan, H., Tashiro, S., Aono, M., Tran, M. T., Pham, V. K., Nguyen, H. D., Nguyen, V. T., Tran, Q. T., Phan, T. V., ... Yeung, S. K. (2017). SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset. In I. Pratikakis, M. Ovsjanikov, & F. Dupont (Eds.), EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval (pp. 25-32). (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. 2017-April). Eurographics Association. https://doi.org/10.2312/3dor.20171048

SHREC'17 : RgB-D to CAD retrieval with ObjectNN dataset. / Hua, Binh Son; Truong, Quang Trung; Tran, Minh Khoi; Pham, Quang Hieu; Kanezaki, Asako; Lee, Tang; Chiang, Hung Yueh; Hsu, Winston; Li, Bo; Lu, Yijuan; Johan, Henry; Tashiro, Shoki; Aono, Masaki; Tran, Minh Triet; Pham, Viet Khoi; Nguyen, Hai Dang; Nguyen, Vinh Tiep; Tran, Quang Thang; Phan, Thuyen V.; Truong, Bao; Do, Minh N.; Duong, Anh Duc; Yu, Lap Fai; Nguyen, Duc Thanh; Yeung, Sai Kit.

EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval. ed. / Ioannis Pratikakis; Maks Ovsjanikov; Florent Dupont. Eurographics Association, 2017. p. 25-32 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. 2017-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hua, BS, Truong, QT, Tran, MK, Pham, QH, Kanezaki, A, Lee, T, Chiang, HY, Hsu, W, Li, B, Lu, Y, Johan, H, Tashiro, S, Aono, M, Tran, MT, Pham, VK, Nguyen, HD, Nguyen, VT, Tran, QT, Phan, TV, Truong, B, Do, MN, Duong, AD, Yu, LF, Nguyen, DT & Yeung, SK 2017, SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset. in I Pratikakis, M Ovsjanikov & F Dupont (eds), EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval. Eurographics Workshop on 3D Object Retrieval, EG 3DOR, vol. 2017-April, Eurographics Association, pp. 25-32, 10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017, Lyon, France, 4/23/17. https://doi.org/10.2312/3dor.20171048

Hua BS, Truong QT, Tran MK, Pham QH, Kanezaki A, Lee T et al. SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset. In Pratikakis I, Ovsjanikov M, Dupont F, editors, EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval. Eurographics Association. 2017. p. 25-32. (Eurographics Workshop on 3D Object Retrieval, EG 3DOR). https://doi.org/10.2312/3dor.20171048

Hua, Binh Son ; Truong, Quang Trung ; Tran, Minh Khoi ; Pham, Quang Hieu ; Kanezaki, Asako ; Lee, Tang ; Chiang, Hung Yueh ; Hsu, Winston ; Li, Bo ; Lu, Yijuan ; Johan, Henry ; Tashiro, Shoki ; Aono, Masaki ; Tran, Minh Triet ; Pham, Viet Khoi ; Nguyen, Hai Dang ; Nguyen, Vinh Tiep ; Tran, Quang Thang ; Phan, Thuyen V. ; Truong, Bao ; Do, Minh N. ; Duong, Anh Duc ; Yu, Lap Fai ; Nguyen, Duc Thanh ; Yeung, Sai Kit. / SHREC'17 : RgB-D to CAD retrieval with ObjectNN dataset. EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval. editor / Ioannis Pratikakis ; Maks Ovsjanikov ; Florent Dupont. Eurographics Association, 2017. pp. 25-32 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR).

@inproceedings{12c3b6c1d5fa4b988a87771093e9812a,

title = "SHREC'17: RgB-D to CAD retrieval with ObjectNN dataset",

abstract = "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.",

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

note = "Funding Information: We acknowledge the support of the SUTD Digital Manufacturing and Design (DManD) Centre which is supported by the National Research Foundation (NRF) of Singapore. Bo Li is partially supported by the University of Southern Mississippi Faculty Startup Funds Award. The research done by Henry Johan is supported by the National Research Foundation, Prime Minister{\textquoteright}s Office, Singapore under its International Research Centres in Singapore Funding Initiative. The research conducted by Lap-Fai Yu is supported by the National Science Foundation under award number 1565978.; 10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017 ; Conference date: 23-04-2017 Through 24-04-2017",

year = "2017",

doi = "10.2312/3dor.20171048",

language = "English (US)",

series = "Eurographics Workshop on 3D Object Retrieval, EG 3DOR",

publisher = "Eurographics Association",

pages = "25--32",

editor = "Ioannis Pratikakis and Maks Ovsjanikov and Florent Dupont",

booktitle = "EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval",

}

TY - GEN

T1 - SHREC'17

T2 - 10th Eurographics Workshop on 3D Object Retrieval, 3DOR 2017

AU - Hua, Binh Son

AU - Truong, Quang Trung

AU - Tran, Minh Khoi

AU - Pham, Quang Hieu

AU - Kanezaki, Asako

AU - Lee, Tang

AU - Chiang, Hung Yueh

AU - Hsu, Winston

AU - Li, Bo

AU - Lu, Yijuan

AU - Johan, Henry

AU - Tashiro, Shoki

AU - Aono, Masaki

AU - Tran, Minh Triet

AU - Pham, Viet Khoi

AU - Nguyen, Hai Dang

AU - Nguyen, Vinh Tiep

AU - Tran, Quang Thang

AU - Phan, Thuyen V.

AU - Truong, Bao

AU - Do, Minh N.

AU - Duong, Anh Duc

AU - Yu, Lap Fai

AU - Nguyen, Duc Thanh

AU - Yeung, Sai Kit

N1 - Funding Information: We acknowledge the support of the SUTD Digital Manufacturing and Design (DManD) Centre which is supported by the National Research Foundation (NRF) of Singapore. Bo Li is partially supported by the University of Southern Mississippi Faculty Startup Funds Award. The research done by Henry Johan is supported by the National Research Foundation, Prime Minister’s Office, Singapore under its International Research Centres in Singapore Funding Initiative. The research conducted by Lap-Fai Yu is supported by the National Science Foundation under award number 1565978.

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85046295367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046295367&partnerID=8YFLogxK

U2 - 10.2312/3dor.20171048

DO - 10.2312/3dor.20171048

M3 - Conference contribution

AN - SCOPUS:85046295367

T3 - Eurographics Workshop on 3D Object Retrieval, EG 3DOR

SP - 25

EP - 32

BT - EG 3DOR 2017 - Eurographics 2017 Workshop on 3D Object Retrieval

A2 - Pratikakis, Ioannis

A2 - Ovsjanikov, Maks

A2 - Dupont, Florent

PB - Eurographics Association

Y2 - 23 April 2017 through 24 April 2017

ER -