Hostname: page-component-cb9f654ff-c75p9 Total loading time: 0 Render date: 2025-08-27T04:55:15.837Z Has data issue: false hasContentIssue false
  • English
  • Français

Exploiting 3D Variational Autoencoders for Interactive Vehicle Design

Published online by Cambridge University Press:  26 May 2022

S. Saha ,
L. L. Minku ,
X. Yao ,
B. Sendhoff  and
S. Menzel
S. Saha*
Affiliation:
Honda Research Institute Europe GmbH, Germany University of Birmingham, United Kingdom
L. L. Minku
Affiliation:
University of Birmingham, United Kingdom
X. Yao
Affiliation:
University of Birmingham, United Kingdom Southern University of Science and Technology, China
B. Sendhoff
Affiliation:
Honda Research Institute Europe GmbH, Germany
S. Menzel
Affiliation:
Honda Research Institute Europe GmbH, Germany
*
sneha.saha@honda-ri.de

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

In automotive digital development, 3D prototype creation is a team effort of designers and engineers, each contributing with ideas and technical evaluations through means of computer simulations. To support the team in the 3D design ideation and exploration task, we propose an interactive design system for assisted design explorations and faster performance estimations. We utilize the advantage of deep learning-based autoencoders to create a low-dimensional latent manifold of 3D designs, which is utilized within an interactive user interface to guide and strengthen the decision-making process.

Keywords

data-driven designcollaborative design3D modelling

Information

Type
Article
Information
Proceedings of the Design Society , Volume 2: DESIGN2022 , May 2022 , pp. 1747 - 1756
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2022.

References

Achlioptas, P., Diamanti, O., Mitliagkas, I. and Guibas, L. (2018), “Learning representations and generative models for 3d point clouds”, International Conference on Machine Learning (ICML), Vol. 80, pp. 40–49. https://arxiv.org/abs/1707.02392.Google Scholar
Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., et al. . (2015), ShapeNet: An Information-Rich 3D Model Repository, available at: http://arxiv.org/abs/1512.03012.Google Scholar
Ha, D. and Eck, D. (2018), “A Neural Representation of Sketch Drawings”, 6th International Conference on Learning Representations, ICLR. https://arxiv.org/abs/1704.03477.Google Scholar
Lee, Y.J., Zitnick, C.L. and Cohen, M.F. (2011), “ShadowDraw: Real-time user guidance for freehand drawing”, ACM Transactions on Graphics, Vol. 30 No. 4, pp. 1–10. 10.1145/2010324.1964922.CrossRefGoogle Scholar
Qi, C.R., Su, H., Mo, K. and Guibas, L.J. (2017), “PointNet: Deep learning on point sets for 3D classification and segmentation”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652–660. https://arxiv.org/abs/1612.00593.Google Scholar
Rios, T., Bäck, T., van Stein, B., Sendhoff, B. and Menzel, S. (2019), “On the Efficiency of a Point Cloud Autoencoder as a Geometric Representation for Shape Optimization”, IEEE Symposium Series on Computational Intelligence (SSCI), pp. 791–798. 10.1109/SSCI44817.2019.9003161.Google Scholar
Saha, S., Menzel, S., Minku, L.L., Yao, X., Sendhoff, B. and Wollstadt, P. (2020), “Quantifying The Generative Capabilities Of Variational Autoencoders For 3D Car Point Clouds”, IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1469–1477. 10.1109/SSCI47803.2020.9308513.CrossRefGoogle Scholar
Saha, S., Minku, L.L., Yao, X., Sendhoff, B. and Menzel, S. (2021a), “Exploiting Linear Interpolation of Variational Autoencoders for Satisfying Preferences in Evolutionary Design Optimization”, IEEE Congress on Evolutionary Computation (CEC), pp. 1767–1776. 10.1109/CEC45853.2021.9504772.CrossRefGoogle Scholar
Saha, S., Rios, T., Minku, L.L., van Stein, B., Wollstadt, P., Yao, X., Bäck, T., Sendhoff, B. and Menzel, S. (2021b), “Exploiting Generative Models for Performance Predictions of 3D Car Designs”, IEEE Symposium Series on Computational Intelligence (SSCI). pp. 1–9. 10.1109/SSCI50451.2021.9660034.Google Scholar
Saltelli, A., Annoni, P., Azzini, I., Campolongo, F., Ratto, M. and Tarantola, S. (2010), “Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index”, Computer Physics Communications, Elsevier B.V., Vol. 181 No. 2, pp. 259–270. 10.1016/j.cpc.2009.09.018.Google Scholar
Sederberg, T.W. and Parry, S.R. (1986), “Free-form deformation of solid geometric models”, ACM Special Interest Group on Computer Graphics and Interactive Techniques, Vol. 20 No. 4, pp. 151–160. 10.1145/15886.15903.Google Scholar
Umetani, N. (2017), “Exploring generative 3D shapes using autoencoder networks”, SIGGRAPH Asia 2017 Technical Briefs, Vol. 4, pp. 1–4. https://dl.acm.org/doi/10.1145/3145749.3145758.Google Scholar