3D Object Classification and Parameter Estimation based on Parametric Procedural Models

Roman Getto, Kenten Fina, Lennart Jarms, Arjan Kuijper, Dieter Fellner

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Classifying and gathering additional information about an unknown 3D objects is dependent on having a large amount of learning data. We propose to use procedural models as data foundation for this task. In our method we (semi-)automatically define parameters for a procedural model constructed with a modeling tool. Then we use the procedural models to classify an object and also automatically estimate the best parameters. We use a standard convolutional neural network and three different object similarity measures to estimate the best parameters at each degree of detail. We evaluate all steps of our approach using several procedural models and show that we can achieve high classification accuracy and meaningful parameters for unknown objects.
LanguageEnglish
Title of host publicationWSCG 2018
EditorsVaclav Skala
PublisherUniversity of West Bohemia
ISBN (Print)978-80-86943-40-4
StatusPublished - 2018
Event26th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision - Pilsen, Czech Republic
Duration: 28 May 20181 Jun 2018

Publication series

NameComputer Science Research Notes
Volume2801

Conference

Conference26th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision
Abbreviated titleWSCG 2018
CountryCzech Republic
CityPilsen
Period28/05/181/06/18

Keywords

  • Procedural modeling
  • Parametric modeling
  • Parameterization
  • 3D Objects
  • Classifications
  • Deep learning
  • Guiding Theme: Digitized Work
  • Research Area: Computer graphics (CG)

Fields of Expertise

  • Information, Communication & Computing

Cite this

Getto, R., Fina, K., Jarms, L., Kuijper, A., & Fellner, D. (2018). 3D Object Classification and Parameter Estimation based on Parametric Procedural Models. In V. Skala (Ed.), WSCG 2018 (Computer Science Research Notes ; Vol. 2801). University of West Bohemia.

3D Object Classification and Parameter Estimation based on Parametric Procedural Models. / Getto, Roman ; Fina, Kenten ; Jarms, Lennart ; Kuijper, Arjan ; Fellner, Dieter.

WSCG 2018. ed. / Vaclav Skala. University of West Bohemia, 2018. (Computer Science Research Notes ; Vol. 2801).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Getto, R, Fina, K, Jarms, L, Kuijper, A & Fellner, D 2018, 3D Object Classification and Parameter Estimation based on Parametric Procedural Models. in V Skala (ed.), WSCG 2018. Computer Science Research Notes , vol. 2801, University of West Bohemia, 26th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision , Pilsen, Czech Republic, 28/05/18.
Getto R, Fina K, Jarms L, Kuijper A, Fellner D. 3D Object Classification and Parameter Estimation based on Parametric Procedural Models. In Skala V, editor, WSCG 2018. University of West Bohemia. 2018. (Computer Science Research Notes ).
Getto, Roman ; Fina, Kenten ; Jarms, Lennart ; Kuijper, Arjan ; Fellner, Dieter. / 3D Object Classification and Parameter Estimation based on Parametric Procedural Models. WSCG 2018. editor / Vaclav Skala. University of West Bohemia, 2018. (Computer Science Research Notes ).
@inproceedings{2ef6392f291d4a9ba99fff94cbf7b2e1,
title = "3D Object Classification and Parameter Estimation based on Parametric Procedural Models",
abstract = "Classifying and gathering additional information about an unknown 3D objects is dependent on having a large amount of learning data. We propose to use procedural models as data foundation for this task. In our method we (semi-)automatically define parameters for a procedural model constructed with a modeling tool. Then we use the procedural models to classify an object and also automatically estimate the best parameters. We use a standard convolutional neural network and three different object similarity measures to estimate the best parameters at each degree of detail. We evaluate all steps of our approach using several procedural models and show that we can achieve high classification accuracy and meaningful parameters for unknown objects.",
keywords = "Procedural modeling, Parametric modeling, Parameterization, 3D Objects, Classifications, Deep learning, Guiding Theme: Digitized Work, Research Area: Computer graphics (CG)",
author = "Roman Getto and Kenten Fina and Lennart Jarms and Arjan Kuijper and Dieter Fellner",
year = "2018",
language = "English",
isbn = "978-80-86943-40-4",
series = "Computer Science Research Notes",
publisher = "University of West Bohemia",
editor = "Vaclav Skala",
booktitle = "WSCG 2018",

}

TY - GEN

T1 - 3D Object Classification and Parameter Estimation based on Parametric Procedural Models

AU - Getto, Roman

AU - Fina, Kenten

AU - Jarms, Lennart

AU - Kuijper, Arjan

AU - Fellner, Dieter

PY - 2018

Y1 - 2018

N2 - Classifying and gathering additional information about an unknown 3D objects is dependent on having a large amount of learning data. We propose to use procedural models as data foundation for this task. In our method we (semi-)automatically define parameters for a procedural model constructed with a modeling tool. Then we use the procedural models to classify an object and also automatically estimate the best parameters. We use a standard convolutional neural network and three different object similarity measures to estimate the best parameters at each degree of detail. We evaluate all steps of our approach using several procedural models and show that we can achieve high classification accuracy and meaningful parameters for unknown objects.

AB - Classifying and gathering additional information about an unknown 3D objects is dependent on having a large amount of learning data. We propose to use procedural models as data foundation for this task. In our method we (semi-)automatically define parameters for a procedural model constructed with a modeling tool. Then we use the procedural models to classify an object and also automatically estimate the best parameters. We use a standard convolutional neural network and three different object similarity measures to estimate the best parameters at each degree of detail. We evaluate all steps of our approach using several procedural models and show that we can achieve high classification accuracy and meaningful parameters for unknown objects.

KW - Procedural modeling

KW - Parametric modeling

KW - Parameterization

KW - 3D Objects

KW - Classifications

KW - Deep learning

KW - Guiding Theme: Digitized Work

KW - Research Area: Computer graphics (CG)

UR - http://wscg.zcu.cz/DL/wscg_DL.htm

M3 - Conference contribution

SN - 978-80-86943-40-4

T3 - Computer Science Research Notes

BT - WSCG 2018

A2 - Skala, Vaclav

PB - University of West Bohemia

ER -