Exploiting 3D variational autoencoders for interactive vehicle design

Sneha Saha; Leandro Minku; Xin Yao; Bernard Sendhoff; Stefan Menzel

doi:10.1017/pds.2022.177

Exploiting 3D variational autoencoders for interactive vehicle design

Sneha Saha, Leandro Minku, Xin Yao, Bernard Sendhoff, Stefan Menzel

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

19 Downloads (Pure)

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.

Original language	English
Title of host publication	DESIGN2022
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 - 26 May 2022
Event	DESIGN 2022: 17th International Design Conference - Online, Croatia Duration: 23 May 2022 → 26 May 2022

Publication series

Name	Proceedings of the Design Society

Conference

Conference	DESIGN 2022
Country/Territory	Croatia
Period	23/05/22 → 26/05/22

Bibliographical note

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

Publisher Copyright:
© The Author(s), 2022.

Keywords

data-driven design
collaborative design
3D modelling

Access to Document

10.1017/pds.2022.177Licence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

SahaS2022ExploitingFinal published version, 843 KBLicence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

H2020_ITN_ECOLE_Coordinator
Yao, X.
European Commission - Management Costs, European Commission
1/04/18 → 31/03/22
Project: Research

Cite this

@inproceedings{9a69237917b04c529045a56e1e058d6c,

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.",

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

author = "Sneha Saha and Leandro Minku and Xin Yao and Bernard Sendhoff and Stefan Menzel",

note = "Funding Information: This project has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE). Publisher Copyright: {\textcopyright} The Author(s), 2022.; DESIGN 2022 : 17th International Design Conference ; Conference date: 23-05-2022 Through 26-05-2022",

year = "2022",

month = may,

day = "26",

doi = "10.1017/pds.2022.177",

language = "English",

volume = "2",

series = "Proceedings of the Design Society",

publisher = "Cambridge University Press",

pages = "1747--1756",

booktitle = "DESIGN2022",

}

TY - GEN

T1 - Exploiting 3D variational autoencoders for interactive vehicle design

AU - Saha, Sneha

AU - Minku, Leandro

AU - Yao, Xin

AU - Sendhoff, Bernard

AU - Menzel, Stefan

N1 - Funding Information: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 766186 (ECOLE). Publisher Copyright: © The Author(s), 2022.

PY - 2022/5/26

Y1 - 2022/5/26

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.

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.

KW - data-driven design

KW - collaborative design

KW - 3D modelling

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 contribution

VL - 2

T3 - Proceedings of the Design Society

SP - 1747

EP - 1756

BT - DESIGN2022

PB - Cambridge University Press

T2 - DESIGN 2022

Y2 - 23 May 2022 through 26 May 2022

ER -

Exploiting 3D variational autoencoders for interactive vehicle design

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Projects

H2020_ITN_ECOLE_Coordinator

Cite this