3D Parametric Wireframe Extraction Based on Distance Fields

Albert Matveev; Alexey Artemov; Denis Zorin; Evgeny Burnaev

doi:10.1145/3488933.3488982

3D Parametric Wireframe Extraction Based on Distance Fields

Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev

Computer Science

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

Abstract

We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.

Original language	English (US)
Title of host publication	AIPR 2021 - 2021 4th International Conference on Artificial Intelligence and Pattern Recognition
Publisher	Association for Computing Machinery
Pages	316-322
Number of pages	7
ISBN (Electronic)	9781450384087
DOIs	https://doi.org/10.1145/3488933.3488982
State	Published - Sep 24 2021
Event	4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2021 - Virtual, Online, China Duration: Sep 17 2021 → Sep 19 2021

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2021
Country/Territory	China
City	Virtual, Online
Period	9/17/21 → 9/19/21

Keywords

Distance fields
Sharp features
Spline fitting

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3488933.3488982

Cite this

3D Parametric Wireframe Extraction Based on Distance Fields. / Matveev, Albert; Artemov, Alexey; Zorin, Denis et al.
AIPR 2021 - 2021 4th International Conference on Artificial Intelligence and Pattern Recognition. Association for Computing Machinery, 2021. p. 316-322 (ACM International Conference Proceeding Series).

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

Matveev, A, Artemov, A, Zorin, D & Burnaev, E 2021, 3D Parametric Wireframe Extraction Based on Distance Fields. in AIPR 2021 - 2021 4th International Conference on Artificial Intelligence and Pattern Recognition. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 316-322, 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2021, Virtual, Online, China, 9/17/21. https://doi.org/10.1145/3488933.3488982

@inproceedings{0f96a332333c469085addd09842b0914,

title = "3D Parametric Wireframe Extraction Based on Distance Fields",

abstract = "We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.",

keywords = "Distance fields, Sharp features, Spline fitting",

author = "Albert Matveev and Alexey Artemov and Denis Zorin and Evgeny Burnaev",

note = "Funding Information: The reported study was funded by RFBR, project number 19-31-90144. Publisher Copyright: {\textcopyright} 2021 ACM.; 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2021 ; Conference date: 17-09-2021 Through 19-09-2021",

year = "2021",

month = sep,

day = "24",

doi = "10.1145/3488933.3488982",

language = "English (US)",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "316--322",

booktitle = "AIPR 2021 - 2021 4th International Conference on Artificial Intelligence and Pattern Recognition",

}

TY - GEN

T1 - 3D Parametric Wireframe Extraction Based on Distance Fields

AU - Matveev, Albert

AU - Artemov, Alexey

AU - Zorin, Denis

AU - Burnaev, Evgeny

PY - 2021/9/24

Y1 - 2021/9/24

N2 - We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.

AB - We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.

KW - Distance fields

KW - Sharp features

KW - Spline fitting

UR - http://www.scopus.com/inward/record.url?scp=85125863754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125863754&partnerID=8YFLogxK

U2 - 10.1145/3488933.3488982

DO - 10.1145/3488933.3488982

M3 - Conference contribution

AN - SCOPUS:85125863754

T3 - ACM International Conference Proceeding Series

SP - 316

EP - 322

BT - AIPR 2021 - 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

PB - Association for Computing Machinery

T2 - 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2021

Y2 - 17 September 2021 through 19 September 2021

ER -

3D Parametric Wireframe Extraction Based on Distance Fields

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this