SHREC'18 track: 2D scene sketch-based 3D scene retrieval

Juefei Yuan, Bo Li, Yijuan Lu, Song Bai, Xiang Bai, Ngoc Minh Bui, Minh N Do, Trong Le Do, Anh Duc Duong, Xinwei He, Tu Khiem Le, Wenhui Li, Anan Liu, Xiaolong Liu, Khac Tuan Nguyen, Vinh Tiep Nguyen, Weizhi Nie, Van Tu Ninh, Yuting Su, Vinh Ton-ThatMinh Triet Tran, Shu Xiang, Heyu Zhou, Yang Zhou, Zhichao Zhou

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

Abstract

Sketch-based 3D model retrieval has the intuitiveness advantage over other types of retrieval schemes. Currently, there is a lot of research in sketch-based 3D model retrieval, which usually targets the problem of retrieving a list of candidate 3D models using a single sketch as input. 2D scene sketch-based 3D scene retrieval is a brand new research topic in the field of 3D object retrieval. Unlike traditional sketch-based 3D model retrieval which ideally assumes that a query sketch contains only a single object, this is a new 3D model retrieval topic within the context of a 2D scene sketch which contains several objects that may overlap with each other and thus be occluded and also have relative location configurations. It is challenging due to the semantic gap existing between the iconic 2D representation of sketches and more accurate 3D representation of 3D models. But it also has vast applications such as 3D scene reconstruction, autonomous driving cars, 3D geometry video retrieval, and 3D AR/VR Entertainment. Therefore, this research topic deserves our further exploration. To promote this interesting research, we organize this SHREC track and build the first 2D scene sketch-based 3D scene retrieval benchmark by collecting 3D scenes from Google 3D Warehouse and utilizing our previously proposed 2D scene sketch dataset Scene250. The objective of this track is to evaluate the performance of different 2D scene sketch-based 3D scene retrieval algorithms using a 2D sketch query dataset and a 3D Warehouse model dataset. The benchmark contains 250 scene sketches and 1000 3D scene models, and both are equally classified into 10 classes. In this track, six groups from five countries (China, Chile, USA, UK, and Vietnam) have registered for the track, while due to many challenges involved, only 3 groups have successfully submitted 8 runs. The retrieval performance of submitted results has been evaluated using 7 commonly used retrieval performance metrics. We also conduct a thorough analysis and discussion on those methods, and suggest several future research directions to tackle this research problem. We wish this publicly available [YLL18] benchmark, comparative evaluation results and corresponding evaluation code, will further enrich and advance the research of 2D scene sketch-based 3D scene retrieval and its applications.

Original languageEnglish (US)
Title of host publicationEG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval
PublisherEurographics Association
Pages29-36
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

Warehouses
Railroad cars
Semantics
Geometry

ASJC Scopus subject areas

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

Cite this

Yuan, J., Li, B., Lu, Y., Bai, S., Bai, X., Bui, N. M., ... Zhou, Z. (2018). SHREC'18 track: 2D scene sketch-based 3D scene retrieval. In EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval (pp. 29-36). (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. 2018-April). Eurographics Association. https://doi.org/10.2312/3dor.20181050

SHREC'18 track : 2D scene sketch-based 3D scene retrieval. / Yuan, Juefei; Li, Bo; Lu, Yijuan; Bai, Song; Bai, Xiang; Bui, Ngoc Minh; Do, Minh N; Do, Trong Le; Duong, Anh Duc; He, Xinwei; Le, Tu Khiem; Li, Wenhui; Liu, Anan; Liu, Xiaolong; Nguyen, Khac Tuan; Nguyen, Vinh Tiep; Nie, Weizhi; Ninh, Van Tu; Su, Yuting; Ton-That, Vinh; Tran, Minh Triet; Xiang, Shu; Zhou, Heyu; Zhou, Yang; Zhou, Zhichao.

EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Association, 2018. p. 29-36 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. 2018-April).

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

Yuan, J, Li, B, Lu, Y, Bai, S, Bai, X, Bui, NM, Do, MN, Do, TL, Duong, AD, He, X, Le, TK, Li, W, Liu, A, Liu, X, Nguyen, KT, Nguyen, VT, Nie, W, Ninh, VT, Su, Y, Ton-That, V, Tran, MT, Xiang, S, Zhou, H, Zhou, Y & Zhou, Z 2018, SHREC'18 track: 2D scene sketch-based 3D scene 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. 29-36, 11th Eurographics Workshop on 3D Object Retrieval, 3DOR 2018, Delft, Netherlands, 4/16/18. https://doi.org/10.2312/3dor.20181050
Yuan J, Li B, Lu Y, Bai S, Bai X, Bui NM et al. SHREC'18 track: 2D scene sketch-based 3D scene retrieval. In EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Association. 2018. p. 29-36. (Eurographics Workshop on 3D Object Retrieval, EG 3DOR). https://doi.org/10.2312/3dor.20181050
Yuan, Juefei ; Li, Bo ; Lu, Yijuan ; Bai, Song ; Bai, Xiang ; Bui, Ngoc Minh ; Do, Minh N ; Do, Trong Le ; Duong, Anh Duc ; He, Xinwei ; Le, Tu Khiem ; Li, Wenhui ; Liu, Anan ; Liu, Xiaolong ; Nguyen, Khac Tuan ; Nguyen, Vinh Tiep ; Nie, Weizhi ; Ninh, Van Tu ; Su, Yuting ; Ton-That, Vinh ; Tran, Minh Triet ; Xiang, Shu ; Zhou, Heyu ; Zhou, Yang ; Zhou, Zhichao. / SHREC'18 track : 2D scene sketch-based 3D scene retrieval. EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval. Eurographics Association, 2018. pp. 29-36 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR).
@inproceedings{793d6c56eb1649588eb753ea54276e98,
title = "SHREC'18 track: 2D scene sketch-based 3D scene retrieval",
abstract = "Sketch-based 3D model retrieval has the intuitiveness advantage over other types of retrieval schemes. Currently, there is a lot of research in sketch-based 3D model retrieval, which usually targets the problem of retrieving a list of candidate 3D models using a single sketch as input. 2D scene sketch-based 3D scene retrieval is a brand new research topic in the field of 3D object retrieval. Unlike traditional sketch-based 3D model retrieval which ideally assumes that a query sketch contains only a single object, this is a new 3D model retrieval topic within the context of a 2D scene sketch which contains several objects that may overlap with each other and thus be occluded and also have relative location configurations. It is challenging due to the semantic gap existing between the iconic 2D representation of sketches and more accurate 3D representation of 3D models. But it also has vast applications such as 3D scene reconstruction, autonomous driving cars, 3D geometry video retrieval, and 3D AR/VR Entertainment. Therefore, this research topic deserves our further exploration. To promote this interesting research, we organize this SHREC track and build the first 2D scene sketch-based 3D scene retrieval benchmark by collecting 3D scenes from Google 3D Warehouse and utilizing our previously proposed 2D scene sketch dataset Scene250. The objective of this track is to evaluate the performance of different 2D scene sketch-based 3D scene retrieval algorithms using a 2D sketch query dataset and a 3D Warehouse model dataset. The benchmark contains 250 scene sketches and 1000 3D scene models, and both are equally classified into 10 classes. In this track, six groups from five countries (China, Chile, USA, UK, and Vietnam) have registered for the track, while due to many challenges involved, only 3 groups have successfully submitted 8 runs. The retrieval performance of submitted results has been evaluated using 7 commonly used retrieval performance metrics. We also conduct a thorough analysis and discussion on those methods, and suggest several future research directions to tackle this research problem. We wish this publicly available [YLL18] benchmark, comparative evaluation results and corresponding evaluation code, will further enrich and advance the research of 2D scene sketch-based 3D scene retrieval and its applications.",
author = "Juefei Yuan and Bo Li and Yijuan Lu and Song Bai and Xiang Bai and Bui, {Ngoc Minh} and Do, {Minh N} and Do, {Trong Le} and Duong, {Anh Duc} and Xinwei He and Le, {Tu Khiem} and Wenhui Li and Anan Liu and Xiaolong Liu and Nguyen, {Khac Tuan} and Nguyen, {Vinh Tiep} and Weizhi Nie and Ninh, {Van Tu} and Yuting Su and Vinh Ton-That and Tran, {Minh Triet} and Shu Xiang and Heyu Zhou and Yang Zhou and Zhichao Zhou",
year = "2018",
month = "1",
day = "1",
doi = "10.2312/3dor.20181050",
language = "English (US)",
series = "Eurographics Workshop on 3D Object Retrieval, EG 3DOR",
publisher = "Eurographics Association",
pages = "29--36",
booktitle = "EG 3DOR 2018 - Eurographics Workshop on 3D Object Retrieval",

}

TY - GEN

T1 - SHREC'18 track

T2 - 2D scene sketch-based 3D scene retrieval

AU - Yuan, Juefei

AU - Li, Bo

AU - Lu, Yijuan

AU - Bai, Song

AU - Bai, Xiang

AU - Bui, Ngoc Minh

AU - Do, Minh N

AU - Do, Trong Le

AU - Duong, Anh Duc

AU - He, Xinwei

AU - Le, Tu Khiem

AU - Li, Wenhui

AU - Liu, Anan

AU - Liu, Xiaolong

AU - Nguyen, Khac Tuan

AU - Nguyen, Vinh Tiep

AU - Nie, Weizhi

AU - Ninh, Van Tu

AU - Su, Yuting

AU - Ton-That, Vinh

AU - Tran, Minh Triet

AU - Xiang, Shu

AU - Zhou, Heyu

AU - Zhou, Yang

AU - Zhou, Zhichao

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Sketch-based 3D model retrieval has the intuitiveness advantage over other types of retrieval schemes. Currently, there is a lot of research in sketch-based 3D model retrieval, which usually targets the problem of retrieving a list of candidate 3D models using a single sketch as input. 2D scene sketch-based 3D scene retrieval is a brand new research topic in the field of 3D object retrieval. Unlike traditional sketch-based 3D model retrieval which ideally assumes that a query sketch contains only a single object, this is a new 3D model retrieval topic within the context of a 2D scene sketch which contains several objects that may overlap with each other and thus be occluded and also have relative location configurations. It is challenging due to the semantic gap existing between the iconic 2D representation of sketches and more accurate 3D representation of 3D models. But it also has vast applications such as 3D scene reconstruction, autonomous driving cars, 3D geometry video retrieval, and 3D AR/VR Entertainment. Therefore, this research topic deserves our further exploration. To promote this interesting research, we organize this SHREC track and build the first 2D scene sketch-based 3D scene retrieval benchmark by collecting 3D scenes from Google 3D Warehouse and utilizing our previously proposed 2D scene sketch dataset Scene250. The objective of this track is to evaluate the performance of different 2D scene sketch-based 3D scene retrieval algorithms using a 2D sketch query dataset and a 3D Warehouse model dataset. The benchmark contains 250 scene sketches and 1000 3D scene models, and both are equally classified into 10 classes. In this track, six groups from five countries (China, Chile, USA, UK, and Vietnam) have registered for the track, while due to many challenges involved, only 3 groups have successfully submitted 8 runs. The retrieval performance of submitted results has been evaluated using 7 commonly used retrieval performance metrics. We also conduct a thorough analysis and discussion on those methods, and suggest several future research directions to tackle this research problem. We wish this publicly available [YLL18] benchmark, comparative evaluation results and corresponding evaluation code, will further enrich and advance the research of 2D scene sketch-based 3D scene retrieval and its applications.

AB - Sketch-based 3D model retrieval has the intuitiveness advantage over other types of retrieval schemes. Currently, there is a lot of research in sketch-based 3D model retrieval, which usually targets the problem of retrieving a list of candidate 3D models using a single sketch as input. 2D scene sketch-based 3D scene retrieval is a brand new research topic in the field of 3D object retrieval. Unlike traditional sketch-based 3D model retrieval which ideally assumes that a query sketch contains only a single object, this is a new 3D model retrieval topic within the context of a 2D scene sketch which contains several objects that may overlap with each other and thus be occluded and also have relative location configurations. It is challenging due to the semantic gap existing between the iconic 2D representation of sketches and more accurate 3D representation of 3D models. But it also has vast applications such as 3D scene reconstruction, autonomous driving cars, 3D geometry video retrieval, and 3D AR/VR Entertainment. Therefore, this research topic deserves our further exploration. To promote this interesting research, we organize this SHREC track and build the first 2D scene sketch-based 3D scene retrieval benchmark by collecting 3D scenes from Google 3D Warehouse and utilizing our previously proposed 2D scene sketch dataset Scene250. The objective of this track is to evaluate the performance of different 2D scene sketch-based 3D scene retrieval algorithms using a 2D sketch query dataset and a 3D Warehouse model dataset. The benchmark contains 250 scene sketches and 1000 3D scene models, and both are equally classified into 10 classes. In this track, six groups from five countries (China, Chile, USA, UK, and Vietnam) have registered for the track, while due to many challenges involved, only 3 groups have successfully submitted 8 runs. The retrieval performance of submitted results has been evaluated using 7 commonly used retrieval performance metrics. We also conduct a thorough analysis and discussion on those methods, and suggest several future research directions to tackle this research problem. We wish this publicly available [YLL18] benchmark, comparative evaluation results and corresponding evaluation code, will further enrich and advance the research of 2D scene sketch-based 3D scene retrieval and its applications.

UR - http://www.scopus.com/inward/record.url?scp=85063029532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063029532&partnerID=8YFLogxK

U2 - 10.2312/3dor.20181050

DO - 10.2312/3dor.20181050

M3 - Conference contribution

AN - SCOPUS:85063029532

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

SP - 29

EP - 36

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

PB - Eurographics Association

ER -