Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board

Qian Wan; Zhicong Lu

doi:10.1145/3544549.3585740

Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

8 Citations (Scopus)

Abstract

During past decades, Artificial Intelligence (AI) has been consistently used in Creativity Support Tools (CSTs). Recently, with the development of generative AI models, particularly Generative Adversarial Nets (GAN) in Computer Vision, it became possible that AI directly generates visual ideas. However, there were rarely any work in creativity research that harnessed the design ideas generated by such models directly for design space exploration. To that end we designed a digital mood board as a technology probe to support semantically-enhanced exploration of the StyleGAN latent space. We compared the mood board with traditional gallery display. Preliminary results showed that such design offered a more enjoyable and explicit way of exploring AI generated visual ideas, but gallery display was found to be more straightforward and less demanding.

© 2023 Copyright held by the owner/author(s).

Original language	English
Title of host publication	CHI EA '23
Subtitle of host publication	Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems
Editors	Albrecht Schmidt, Kaisa Väänänen, Tesh Goyal, Per Ola Kristensson, Anicia Peters
Publisher	Association for Computing Machinery
ISBN (Print)	978-1-4503-9422-2
DOIs	https://doi.org/10.1145/3544549.3585740
Publication status	Published - Apr 2023
Event	2023 CHI Conference on Human Factors in Computing Systems (CHI ’23): reCHInnecting - Hybrid, Hamburg, Germany Duration: 23 Apr 2023 → 28 Apr 2023 https://dl.acm.org/doi/proceedings/10.1145/3544548 https://chi2023.acm.org/

Conference

Conference	2023 CHI Conference on Human Factors in Computing Systems (CHI ’23)
Abbreviated title	CHI 2023
Country/Territory	Germany
City	Hamburg
Period	23/04/23 → 28/04/23
Internet address	https://dl.acm.org/doi/proceedings/10.1145/3544548 https://chi2023.acm.org/

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Research Keywords

creativity support
ideation
human-AI interaction
digital mood board

Access Output

10.1145/3544549.3585740

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Wan, Q., & Lu, Z. (2023). Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board. In A. Schmidt, K. Väänänen, T. Goyal, P. O. Kristensson, & A. Peters (Eds.), CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems Association for Computing Machinery. https://doi.org/10.1145/3544549.3585740

@inproceedings{37d26a8dd22e4e47931b4064fd17d072,

title = "Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board",

abstract = "During past decades, Artificial Intelligence (AI) has been consistently used in Creativity Support Tools (CSTs). Recently, with the development of generative AI models, particularly Generative Adversarial Nets (GAN) in Computer Vision, it became possible that AI directly generates visual ideas. However, there were rarely any work in creativity research that harnessed the design ideas generated by such models directly for design space exploration. To that end we designed a digital mood board as a technology probe to support semantically-enhanced exploration of the StyleGAN latent space. We compared the mood board with traditional gallery display. Preliminary results showed that such design offered a more enjoyable and explicit way of exploring AI generated visual ideas, but gallery display was found to be more straightforward and less demanding.{\textcopyright} 2023 Copyright held by the owner/author(s).",

keywords = "creativity support, ideation, human-AI interaction, digital mood board",

author = "Qian Wan and Zhicong Lu",

note = "Research Unit(s) information for this publication is provided by the author(s) concerned.; 2023 CHI Conference on Human Factors in Computing Systems (CHI {\textquoteright}23) : reCHInnecting, CHI 2023 ; Conference date: 23-04-2023 Through 28-04-2023",

year = "2023",

month = apr,

doi = "10.1145/3544549.3585740",

language = "English",

isbn = "978-1-4503-9422-2",

editor = "Albrecht Schmidt and Kaisa V{\"a}{\"a}n{\"a}nen and Tesh Goyal and Kristensson, {Per Ola} and Anicia Peters",

booktitle = "CHI EA '23",

publisher = "Association for Computing Machinery",

address = "United States",

url = "https://dl.acm.org/doi/proceedings/10.1145/3544548, https://chi2023.acm.org/",

}

Wan, Q & Lu, Z 2023, Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board. in A Schmidt, K Väänänen, T Goyal, PO Kristensson & A Peters (eds), CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23), Hamburg, Germany, 23/04/23. https://doi.org/10.1145/3544549.3585740

Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board. / Wan, Qian ; Lu, Zhicong.
CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems. ed. / Albrecht Schmidt; Kaisa Väänänen; Tesh Goyal; Per Ola Kristensson; Anicia Peters. Association for Computing Machinery, 2023.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board

AU - Wan, Qian

AU - Lu, Zhicong

N1 - Research Unit(s) information for this publication is provided by the author(s) concerned.

PY - 2023/4

Y1 - 2023/4

N2 - During past decades, Artificial Intelligence (AI) has been consistently used in Creativity Support Tools (CSTs). Recently, with the development of generative AI models, particularly Generative Adversarial Nets (GAN) in Computer Vision, it became possible that AI directly generates visual ideas. However, there were rarely any work in creativity research that harnessed the design ideas generated by such models directly for design space exploration. To that end we designed a digital mood board as a technology probe to support semantically-enhanced exploration of the StyleGAN latent space. We compared the mood board with traditional gallery display. Preliminary results showed that such design offered a more enjoyable and explicit way of exploring AI generated visual ideas, but gallery display was found to be more straightforward and less demanding.© 2023 Copyright held by the owner/author(s).

AB - During past decades, Artificial Intelligence (AI) has been consistently used in Creativity Support Tools (CSTs). Recently, with the development of generative AI models, particularly Generative Adversarial Nets (GAN) in Computer Vision, it became possible that AI directly generates visual ideas. However, there were rarely any work in creativity research that harnessed the design ideas generated by such models directly for design space exploration. To that end we designed a digital mood board as a technology probe to support semantically-enhanced exploration of the StyleGAN latent space. We compared the mood board with traditional gallery display. Preliminary results showed that such design offered a more enjoyable and explicit way of exploring AI generated visual ideas, but gallery display was found to be more straightforward and less demanding.© 2023 Copyright held by the owner/author(s).

KW - creativity support

KW - ideation

KW - human-AI interaction

KW - digital mood board

UR - http://www.scopus.com/inward/record.url?scp=85158146535&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85158146535&origin=recordpage

U2 - 10.1145/3544549.3585740

DO - 10.1145/3544549.3585740

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-4503-9422-2

BT - CHI EA '23

A2 - Schmidt, Albrecht

A2 - Väänänen, Kaisa

A2 - Goyal, Tesh

A2 - Kristensson, Per Ola

A2 - Peters, Anicia

PB - Association for Computing Machinery

T2 - 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23)

Y2 - 23 April 2023 through 28 April 2023

ER -

Investigating Semantically-enhanced Exploration of GAN Latent Space via a Digital Mood Board

Abstract

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this