Generating Diverse Indoor Furniture Arrangements

Ya Chuan Hsu; Matthew Fontaine; Sam Earle; Maria Edwards; Julian Togelius; Stefanos Nikolaidis

doi:10.1145/3532719.3543244

Generating Diverse Indoor Furniture Arrangements

Ya Chuan Hsu, Matthew Fontaine, Sam Earle, Maria Edwards, Julian Togelius, Stefanos Nikolaidis

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

Abstract

We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such as the total price of all furniture in the room and the number of pieces placed. To generate realistic furniture arrangement, we train a generative adversarial network (GAN) on human-designed layouts. To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection. Experiments show our approach discovers a set of arrangements that are similar to human-designed layouts but varies in price and number of furniture pieces.

Original language	English (US)
Title of host publication	Proceedings - SIGGRAPH 2022 Posters
Editors	Stephen N. Spencer
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450393614
DOIs	https://doi.org/10.1145/3532719.3543244
State	Published - Jul 27 2022
Event	Special Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2022 - Vancouver, Canada Duration: Aug 7 2022 → Aug 11 2022

Publication series

Name	Proceedings - SIGGRAPH 2022 Posters

Conference

Conference	Special Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2022
Country/Territory	Canada
City	Vancouver
Period	8/7/22 → 8/11/22

Keywords

Furniture arrangement
Generative adversarial network
Latent space illumination
Quality-diversity algorithm

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Human-Computer Interaction

Access to Document

10.1145/3532719.3543244

Cite this

Hsu, YC, Fontaine, M, Earle, S, Edwards, M, Togelius, J & Nikolaidis, S 2022, Generating Diverse Indoor Furniture Arrangements. in SN Spencer (ed.), Proceedings - SIGGRAPH 2022 Posters., 60, Proceedings - SIGGRAPH 2022 Posters, Association for Computing Machinery, Inc, Special Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2022, Vancouver, Canada, 8/7/22. https://doi.org/10.1145/3532719.3543244

@inproceedings{7a9d53601be74666afe0f6217188f3e5,

title = "Generating Diverse Indoor Furniture Arrangements",

abstract = "We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such as the total price of all furniture in the room and the number of pieces placed. To generate realistic furniture arrangement, we train a generative adversarial network (GAN) on human-designed layouts. To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection. Experiments show our approach discovers a set of arrangements that are similar to human-designed layouts but varies in price and number of furniture pieces.",

keywords = "Furniture arrangement, Generative adversarial network, Latent space illumination, Quality-diversity algorithm",

author = "Hsu, {Ya Chuan} and Matthew Fontaine and Sam Earle and Maria Edwards and Julian Togelius and Stefanos Nikolaidis",

note = "Publisher Copyright: {\textcopyright} 2022 Owner/Author.; Special Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2022 ; Conference date: 07-08-2022 Through 11-08-2022",

year = "2022",

month = jul,

day = "27",

doi = "10.1145/3532719.3543244",

language = "English (US)",

series = "Proceedings - SIGGRAPH 2022 Posters",

publisher = "Association for Computing Machinery, Inc",

editor = "Spencer, {Stephen N.}",

booktitle = "Proceedings - SIGGRAPH 2022 Posters",

}

TY - GEN

T1 - Generating Diverse Indoor Furniture Arrangements

AU - Hsu, Ya Chuan

AU - Fontaine, Matthew

AU - Earle, Sam

AU - Edwards, Maria

AU - Togelius, Julian

AU - Nikolaidis, Stefanos

PY - 2022/7/27

Y1 - 2022/7/27

N2 - We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such as the total price of all furniture in the room and the number of pieces placed. To generate realistic furniture arrangement, we train a generative adversarial network (GAN) on human-designed layouts. To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection. Experiments show our approach discovers a set of arrangements that are similar to human-designed layouts but varies in price and number of furniture pieces.

AB - We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such as the total price of all furniture in the room and the number of pieces placed. To generate realistic furniture arrangement, we train a generative adversarial network (GAN) on human-designed layouts. To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection. Experiments show our approach discovers a set of arrangements that are similar to human-designed layouts but varies in price and number of furniture pieces.

KW - Furniture arrangement

KW - Generative adversarial network

KW - Latent space illumination

KW - Quality-diversity algorithm

UR - http://www.scopus.com/inward/record.url?scp=85136228297&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85136228297&partnerID=8YFLogxK

U2 - 10.1145/3532719.3543244

DO - 10.1145/3532719.3543244

M3 - Conference contribution

AN - SCOPUS:85136228297

T3 - Proceedings - SIGGRAPH 2022 Posters

BT - Proceedings - SIGGRAPH 2022 Posters

A2 - Spencer, Stephen N.

PB - Association for Computing Machinery, Inc

T2 - Special Interest Group on Computer Graphics and Interactive Techniques Conference - Posters, SIGGRAPH 2022

Y2 - 7 August 2022 through 11 August 2022

ER -

Generating Diverse Indoor Furniture Arrangements

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this