Getto, Roman and Fina, Kenten and Jarms, Lennart and Kuijper, Arjan and Fellner, Dieter W. (2018):
3D Object Classification and Parameter Estimation based on Parametric Procedural Models.
In: Computer Science Research Notes (CSRN), 2801, In: WSCG 2018. Full Papers Proceedings, p. 10,
Plzen, International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), Plzen, Czech Republic, 2018, ISBN 978-80-86943-40-4,
[Conference or Workshop Item]
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.
Item Type: | Conference or Workshop Item |
---|---|
Erschienen: | 2018 |
Creators: | Getto, Roman and Fina, Kenten and Jarms, Lennart and Kuijper, Arjan and Fellner, Dieter W. |
Title: | 3D Object Classification and Parameter Estimation based on Parametric Procedural Models |
Language: | English |
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. |
Title of Book: | WSCG 2018. Full Papers Proceedings |
Series Name: | Computer Science Research Notes (CSRN) |
Volume: | 2801 |
Place of Publication: | Plzen |
ISBN: | 978-80-86943-40-4 |
Uncontrolled Keywords: | Procedural modeling, Parametric modeling, Parameterization, 3D Objects, Classifications, Deep learning |
Divisions: | 20 Department of Computer Science 20 Department of Computer Science > Interactive Graphics Systems 20 Department of Computer Science > Mathematical and Applied Visual Computing |
Event Title: | International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) |
Event Location: | Plzen, Czech Republic |
Event Dates: | 2018 |
Date Deposited: | 10 Jul 2019 12:13 |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
![]() |
Send an inquiry |
Options (only for editors)
![]() |
Show editorial Details |