Data-driven shape analysis and processing

Kai Xu; Vladimir G. Kim; Qixing Huang; Niloy Mitra; Evangelos Kalogerakis

doi:10.1145/2988458.2988473

Data-driven shape analysis and processing

Kai Xu, Vladimir G. Kim, Qixing Huang, Niloy Mitra, Evangelos Kalogerakis

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

57 Scopus citations

Abstract

Data-driven methods serve an increasingly important role in discovering geometric, structural, and semantic relationships between shapes. In contrast to traditional approaches that process shapes in isolation of each other, data-driven methods aggregate information from 3D model collections to improve the analysis, modeling and editing of shapes. Through reviewing the literature, we provide an overview of the main concepts and components of these methods, as well as discuss their application to classification, segmentation, matching, reconstruction, modeling and exploration, as well as scene analysis and synthesis. We conclude our report with ideas that can inspire future research in data-driven shape analysis and processing.

Original language	English (US)
Title of host publication	SA 2016 - SIGGRAPH ASIA 2016 Courses
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450345385
DOIs	https://doi.org/10.1145/2988458.2988473
State	Published - Nov 28 2016
Externally published	Yes
Event	2016 SIGGRAPH ASIA Courses, SA 2016 - Macau, China Duration: Dec 5 2016 → Dec 8 2016

Publication series

Name	SA 2016 - SIGGRAPH ASIA 2016 Courses

Other

Other	2016 SIGGRAPH ASIA Courses, SA 2016
Country/Territory	China
City	Macau
Period	12/5/16 → 12/8/16

Keywords

Geometry analysis
Geometry processing
Machine learning

ASJC Scopus subject areas

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

Access to Document

10.1145/2988458.2988473

Cite this

@inproceedings{057c61f9735d4e23a802b362417df026,

title = "Data-driven shape analysis and processing",

abstract = "Data-driven methods serve an increasingly important role in discovering geometric, structural, and semantic relationships between shapes. In contrast to traditional approaches that process shapes in isolation of each other, data-driven methods aggregate information from 3D model collections to improve the analysis, modeling and editing of shapes. Through reviewing the literature, we provide an overview of the main concepts and components of these methods, as well as discuss their application to classification, segmentation, matching, reconstruction, modeling and exploration, as well as scene analysis and synthesis. We conclude our report with ideas that can inspire future research in data-driven shape analysis and processing.",

keywords = "Geometry analysis, Geometry processing, Machine learning",

author = "Kai Xu and Kim, {Vladimir G.} and Qixing Huang and Niloy Mitra and Evangelos Kalogerakis",

note = "Funding Information: We thank Zimo Li for proofreading this survey and the anonymous reviewers for helpful suggestions. Kalogerakis gratefully acknowledges support from NSF (CHS-1422441). Kai Xu is supported by NSFC (61572507, 61202333 and 61532003).; 2016 SIGGRAPH ASIA Courses, SA 2016 ; Conference date: 05-12-2016 Through 08-12-2016",

year = "2016",

month = nov,

day = "28",

doi = "10.1145/2988458.2988473",

language = "English (US)",

series = "SA 2016 - SIGGRAPH ASIA 2016 Courses",

publisher = "Association for Computing Machinery, Inc",

booktitle = "SA 2016 - SIGGRAPH ASIA 2016 Courses",

}

TY - GEN

T1 - Data-driven shape analysis and processing

AU - Xu, Kai

AU - Kim, Vladimir G.

AU - Huang, Qixing

AU - Mitra, Niloy

AU - Kalogerakis, Evangelos

N1 - Funding Information: We thank Zimo Li for proofreading this survey and the anonymous reviewers for helpful suggestions. Kalogerakis gratefully acknowledges support from NSF (CHS-1422441). Kai Xu is supported by NSFC (61572507, 61202333 and 61532003).

PY - 2016/11/28

Y1 - 2016/11/28

N2 - Data-driven methods serve an increasingly important role in discovering geometric, structural, and semantic relationships between shapes. In contrast to traditional approaches that process shapes in isolation of each other, data-driven methods aggregate information from 3D model collections to improve the analysis, modeling and editing of shapes. Through reviewing the literature, we provide an overview of the main concepts and components of these methods, as well as discuss their application to classification, segmentation, matching, reconstruction, modeling and exploration, as well as scene analysis and synthesis. We conclude our report with ideas that can inspire future research in data-driven shape analysis and processing.

AB - Data-driven methods serve an increasingly important role in discovering geometric, structural, and semantic relationships between shapes. In contrast to traditional approaches that process shapes in isolation of each other, data-driven methods aggregate information from 3D model collections to improve the analysis, modeling and editing of shapes. Through reviewing the literature, we provide an overview of the main concepts and components of these methods, as well as discuss their application to classification, segmentation, matching, reconstruction, modeling and exploration, as well as scene analysis and synthesis. We conclude our report with ideas that can inspire future research in data-driven shape analysis and processing.

KW - Geometry analysis

KW - Geometry processing

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85007210866&partnerID=8YFLogxK

U2 - 10.1145/2988458.2988473

DO - 10.1145/2988458.2988473

M3 - Conference contribution

AN - SCOPUS:85007210866

T3 - SA 2016 - SIGGRAPH ASIA 2016 Courses

BT - SA 2016 - SIGGRAPH ASIA 2016 Courses

PB - Association for Computing Machinery, Inc

T2 - 2016 SIGGRAPH ASIA Courses, SA 2016

Y2 - 5 December 2016 through 8 December 2016

ER -

Data-driven shape analysis and processing

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this