Hostname: page-component-586b7cd67f-g8jcs Total loading time: 0 Render date: 2024-11-22T10:40:44.208Z Has data issue: false hasContentIssue false
  • English
  • Français

RAPID CREATION OF VEHICLE LINE-UPS BY EIGENSPACE PROJECTIONS FOR STYLE TRANSFER

Part of: Design Methods

Published online by Cambridge University Press:  11 June 2020

T. Friedrich ,
S. Schmitt  and
S. Menzel
T. Friedrich*
Affiliation:
Honda Research Institute Europe GmbH, Germany
S. Schmitt
Affiliation:
Honda Research Institute Europe GmbH, Germany
S. Menzel
Affiliation:
Honda Research Institute Europe GmbH, Germany
*
*[email protected]

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 product development, an automated generation of shape variations enables a rapid assessment of potentially appealing design directions. We present a framework for computing a product line-up of automotive body shapes based on spectral methods for mesh processing. We calculate the eigenspace projections of 3D vehicle meshes and identify the relevant style as well as content components based on the eigenvalues. The style of a model is then transferred to arbitrary prototype content car shapes, which allows for a rapid portfolio generation of various car types with minimal user interaction.

Keywords

3D modellingconceptual designproduct familiesstyle transfercomputational design methods
Type
Article
Information
Proceedings of the Design Society: DESIGN Conference , Volume 1 , May 2020 , pp. 867 - 876
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), 2020. Published by Cambridge University Press

References

Achlioptas, P. et al. (2018), “Learning representations and generative models for 3d point clouds”, in 35th International Conference on Machine Learning, ICML 2018. pp. 67–85. Available at: http://arxiv.org/abs/1707.02392 (accessed 14 November 2019)Google Scholar
Brock, A. et al. (2016), “Generative and Discriminative Voxel Modeling with Convolutional Neural Networks”. Available at: http://arxiv.org/abs/1608.04236 (accessed 14 November 2019).Google Scholar
Friedrich, T., Aulig, N. and Menzel, S. (2018), “On the Potential and Challenges of Neural Style Transfer for Three-dimensional Shape Data”, EngOpt 2018: Proceedings of the 6th International Conference on Engineering Optimization, Springer International Publishing. https://doi.org/10.1007/978-3-319-97773-7CrossRefGoogle Scholar
Friedrich, T. and Menzel, S. (2019), “Standardization Of Gram Matrix For Improved 3D Neural Style Transfer”, 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China. (accepted).CrossRefGoogle Scholar
Gatys, L., Ecker, A. and Bethge, M. (2016), “A Neural Algorithm of Artistic Style”, Journal of Vision, Vol. 16 No. 12. https://doi.org/10.1167/16.12.326CrossRefGoogle Scholar
Jing, Y. et al. (2017), “Neural Style Transfer: A Review”, pp. 1–25. Available at: http://arxiv.org/abs/1705.04058.Google Scholar
Kato, H., Ushiku, Y. and Harada, T. (2018), “Neural 3D Mesh Renderer”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3907–3916. https://doi.org/10.1109/CVPR.2018.00411CrossRefGoogle Scholar
Meyer, M. et al. (2003), “Discrete Differential-Geometry Operators for Triangulated 2-Manifolds”, Visualization and Mathematics III, pp. 35–57. https://doi.org/10.1007/978-3-662-05105-4_2.CrossRefGoogle Scholar
Pinkall, U. and Polthier, K. (1993), “Computing discrete minimal surfaces and their conjugates”, Experimental Mathematics, Vol. 2 No. 1, pp. 15–36, https://doi.org/10.1080/10586458.1993.10504266.CrossRefGoogle Scholar
Reuter, M., Wolter, F.E. and Peinecke, N. (2006), “Laplace-Beltrami spectra as ‘Shape-DNA’ of surfaces and solids”, CAD Computer Aided Design, Vol. 38 No. 4, pp. 342–366, https://doi.org/10.1016/j.cad.2005.10.011.CrossRefGoogle Scholar
Sorkine, O. et al. (2004), Laplacian Surface Editing, Eurographics Symposium on Geometry Processing.CrossRefGoogle Scholar
Sorkine, O. (2005), “Laplacian Mesh Processing”, Eurographics, (Section 4), pp. 53–70, https://doi.org/10.1128/JVI.00468-10.Google Scholar
Umetani, N. (2017), “Exploring Generative 3D Shapes Using Autoen-coder Networks”, SIGGRAPH Asia Technical Brief. https://doi.org/10.1145/3145749.3145758.CrossRefGoogle Scholar
Yang, Z., Jiang, H. and Zou, L. (2019), “3D Conceptual Design Using Deep Learning”, Science and Information Conference. Springer, pp. 16–26. https://doi.org/10.1007/978-3-030-17795-9_2CrossRefGoogle Scholar
Zhang, H., Van Kaick, O. and Dyer, R. (2007), “Spectral Methods for Mesh Processing and Analysis”, {STAR} Proceedings of Eurographics, Vol. 92 No. RC-20404, pp. 1–22, https://doi.org/10.1.1.132.8135.Google Scholar