Exploiting 3D Variational Autoencoders for Interactive Vehicle Design

S. SAHA; L.L. MINKU; X. YAO; B. SENDHOFF; S. MENZEL

doi:10.1017/pds.2022.177

Exploiting 3D Variational Autoencoders for Interactive Vehicle Design

S. SAHA, L.L. MINKU, X. YAO, B. SENDHOFF, S. MENZEL

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

2 Citations (Scopus)

Abstract

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. © The Author(s), 2022.

Original language	English
Title of host publication	Proceedings of the Design Society
Publisher	Cambridge University Press
Pages	1747-1756
Number of pages	10
Volume	2
DOIs	https://doi.org/10.1017/pds.2022.177
Publication status	Published - May 2022
Externally published	Yes

Bibliographical note

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE).

Keywords

3D modelling
collaborative design
data-driven design

Access to Document

10.1017/pds.2022.177Licence: CC BY-NC-ND

Cite this

@inproceedings{cc123576d28c405ebe1837c55998c7f8,

title = "Exploiting 3D Variational Autoencoders for Interactive Vehicle Design",

abstract = "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. {\textcopyright} The Author(s), 2022.",

keywords = "3D modelling, collaborative design, data-driven design",

author = "S. SAHA and L.L. MINKU and X. YAO and B. SENDHOFF and S. MENZEL",

note = "This project has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE).",

year = "2022",

month = may,

doi = "10.1017/pds.2022.177",

language = "English",

volume = "2",

pages = "1747--1756",

booktitle = "Proceedings of the Design Society",

publisher = "Cambridge University Press",

address = "United States",

}

TY - GEN

T1 - Exploiting 3D Variational Autoencoders for Interactive Vehicle Design

AU - SAHA, S.

AU - MINKU, L.L.

AU - YAO, X.

AU - SENDHOFF, B.

AU - MENZEL, S.

N1 - This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE).

PY - 2022/5

Y1 - 2022/5

N2 - 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. © The Author(s), 2022.

AB - 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. © The Author(s), 2022.

KW - 3D modelling

KW - collaborative design

KW - data-driven design

UR - http://www.scopus.com/inward/record.url?scp=85131380870&partnerID=8YFLogxK

U2 - 10.1017/pds.2022.177

DO - 10.1017/pds.2022.177

M3 - Conference paper (refereed)

VL - 2

SP - 1747

EP - 1756

BT - Proceedings of the Design Society

PB - Cambridge University Press

ER -

Exploiting 3D Variational Autoencoders for Interactive Vehicle Design

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this