SHREC'18

RgB-D object-to-cad retrieval

Quang Hieu Pham, Minh Khoi Tran, Wenhui Li, Shu Xiang, Heyu Zhou, Weizhi Nie, Anan Liu, Yuting Su, Minh Triet Tran, Ngoc Minh Bui, Trong Le Do, Tu V. Ninh, Tu Khiem Le, Anh Vu Dao, Vinh Tiep Nguyen, Minh N Do, Anh Duc Duong, Binh Son Hua, Lap Fai Yu, Duc Thanh Nguyen & 1 others Sai Kit Yeung

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

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 [HTT17] to include RGB-D objects from both SceneNN [HPN16] and ScanNet [DCS17], with the CAD models from ShapeNetSem [CFG15]. 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.

Original languageEnglish (US)
Title of host publicationEG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval
PublisherEurographics Association
Pages45-52
Number of pages8
ISBN (Electronic)9783038680536
DOIs
StatePublished - Jan 1 2018
Event11th Eurographics Workshop on 3D Object Retrieval, 3DOR 2018 - Delft, Netherlands
Duration: Apr 16 2018 → …

Publication series

NameEurographics Workshop on 3D Object Retrieval, EG 3DOR
Volume2018-April
ISSN (Print)1997-0463
ISSN (Electronic)1997-0471

Conference

Conference11th Eurographics Workshop on 3D Object Retrieval, 3DOR 2018
CountryNetherlands
CityDelft
Period4/16/18 → …

Fingerprint

Computer aided design
Sensors
Deep learning

ASJC Scopus subject areas

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

Cite this

Pham, Q. H., Tran, M. K., Li, W., Xiang, S., Zhou, H., Nie, W., ... Yeung, S. K. (2018). SHREC'18: RgB-D object-to-cad retrieval. In EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval (pp. 45-52). (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. 2018-April). Eurographics Association. https://doi.org/10.2312/3dor.20181052

SHREC'18 : RgB-D object-to-cad retrieval. / Pham, Quang Hieu; Tran, Minh Khoi; Li, Wenhui; Xiang, Shu; Zhou, Heyu; Nie, Weizhi; Liu, Anan; Su, Yuting; Tran, Minh Triet; Bui, Ngoc Minh; Do, Trong Le; Ninh, Tu V.; Le, Tu Khiem; Dao, Anh Vu; Nguyen, Vinh Tiep; Do, Minh N; Duong, Anh Duc; Hua, Binh Son; Yu, Lap Fai; Nguyen, Duc Thanh; Yeung, Sai Kit.

EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Association, 2018. p. 45-52 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. 2018-April).

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

Pham, QH, Tran, MK, Li, W, Xiang, S, Zhou, H, Nie, W, Liu, A, Su, Y, Tran, MT, Bui, NM, Do, TL, Ninh, TV, Le, TK, Dao, AV, Nguyen, VT, Do, MN, Duong, AD, Hua, BS, Yu, LF, Nguyen, DT & Yeung, SK 2018, SHREC'18: RgB-D object-to-cad retrieval. in EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Workshop on 3D Object Retrieval, EG 3DOR, vol. 2018-April, Eurographics Association, pp. 45-52, 11th Eurographics Workshop on 3D Object Retrieval, 3DOR 2018, Delft, Netherlands, 4/16/18. https://doi.org/10.2312/3dor.20181052
Pham QH, Tran MK, Li W, Xiang S, Zhou H, Nie W et al. SHREC'18: RgB-D object-to-cad retrieval. In EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Association. 2018. p. 45-52. (Eurographics Workshop on 3D Object Retrieval, EG 3DOR). https://doi.org/10.2312/3dor.20181052
Pham, Quang Hieu ; Tran, Minh Khoi ; Li, Wenhui ; Xiang, Shu ; Zhou, Heyu ; Nie, Weizhi ; Liu, Anan ; Su, Yuting ; Tran, Minh Triet ; Bui, Ngoc Minh ; Do, Trong Le ; Ninh, Tu V. ; Le, Tu Khiem ; Dao, Anh Vu ; Nguyen, Vinh Tiep ; Do, Minh N ; Duong, Anh Duc ; Hua, Binh Son ; Yu, Lap Fai ; Nguyen, Duc Thanh ; Yeung, Sai Kit. / SHREC'18 : RgB-D object-to-cad retrieval. EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Association, 2018. pp. 45-52 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR).
@inproceedings{5c80129ae322403b97f88039fdef105d,
title = "SHREC'18: RgB-D object-to-cad retrieval",
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.",
author = "Pham, {Quang Hieu} and Tran, {Minh Khoi} and Wenhui Li and Shu Xiang and Heyu Zhou and Weizhi Nie and Anan Liu and Yuting Su and Tran, {Minh Triet} and Bui, {Ngoc Minh} 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 Yeung, {Sai Kit}",
year = "2018",
month = "1",
day = "1",
doi = "10.2312/3dor.20181052",
language = "English (US)",
series = "Eurographics Workshop on 3D Object Retrieval, EG 3DOR",
publisher = "Eurographics Association",
pages = "45--52",
booktitle = "EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval",

}

TY - GEN

T1 - SHREC'18

T2 - RgB-D object-to-cad retrieval

AU - Pham, Quang Hieu

AU - Tran, Minh Khoi

AU - Li, Wenhui

AU - Xiang, Shu

AU - Zhou, Heyu

AU - Nie, Weizhi

AU - Liu, Anan

AU - Su, Yuting

AU - Tran, Minh Triet

AU - Bui, Ngoc Minh

AU - Do, Trong Le

AU - Ninh, Tu V.

AU - Le, Tu Khiem

AU - Dao, Anh Vu

AU - Nguyen, Vinh Tiep

AU - Do, Minh N

AU - Duong, Anh Duc

AU - Hua, Binh Son

AU - Yu, Lap Fai

AU - Nguyen, Duc Thanh

AU - Yeung, Sai Kit

PY - 2018/1/1

Y1 - 2018/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85063033414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063033414&partnerID=8YFLogxK

U2 - 10.2312/3dor.20181052

DO - 10.2312/3dor.20181052

M3 - Conference contribution

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

SP - 45

EP - 52

BT - EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval

PB - Eurographics Association

ER -