Exploring a Digital Art Collection through Drawing Interactions with a Deep Generative Model

Christian Sivertsen; René Haas; Halfdan Hauch Jensen; Anders Sundnes Løvlie

doi:10.1145/3544549.3583902

Exploring a Digital Art Collection through Drawing Interactions with a Deep Generative Model

Christian Sivertsen, René Haas, Halfdan Hauch Jensen, Anders Sundnes Løvlie

Research output: Conference Article in Proceeding or Book/Report chapter › Conference abstract in proceedings › Research

Abstract

New Snow is an interactive drawing table that investigates human interaction with a deep generative model based on Edvard Munch’s sketching practice. Through drawings with pen and paper, the user can interact with the model which will return synthetic sketches based on the input drawings in real time. The model is a reflection of the training data, and it is thus constrained to representing images within the latent space of Edvard Munch’s sketching practice. As the user familiarizes themselves with the model it allows them to become sensitized to the visual aesthetic belonging to this practice. This potential for familiarization with the aesthetic of a dataset via the model has implications for human-AI interaction and non-verbal art mediation.

Original language	English
Title of host publication	CHI EA '23 : Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems
Number of pages	5
Publisher	Association for Computing Machinery
Publication date	19 Apr 2023
Pages	1-5
Article number	451
ISBN (Electronic)	978-1-4503-9422-2/23/04
DOIs	https://doi.org/10.1145/3544549.3583902
Publication status	Published - 19 Apr 2023

Keywords

Interactive Drawing Table
Human-AI Interaction
Generative Model
Edvard Munch
Visual Aesthetics

Access to Document

10.1145/3544549.3583902

New_Snow___CHI_Interactivity_2023-submitted-versionAccepted author manuscript, 7.81 MB

https://dl.acm.org/doi/pdf/10.1145/3544549.3583902

Cite this

@inbook{192a7e77f4ba4bcea7f43f89c222d9de,

title = "Exploring a Digital Art Collection through Drawing Interactions with a Deep Generative Model",

abstract = "New Snow is an interactive drawing table that investigates human interaction with a deep generative model based on Edvard Munch{\textquoteright}s sketching practice. Through drawings with pen and paper, the user can interact with the model which will return synthetic sketches based on the input drawings in real time. The model is a reflection of the training data, and it is thus constrained to representing images within the latent space of Edvard Munch{\textquoteright}s sketching practice. As the user familiarizes themselves with the model it allows them to become sensitized to the visual aesthetic belonging to this practice. This potential for familiarization with the aesthetic of a dataset via the model has implications for human-AI interaction and non-verbal art mediation.",

keywords = "Interactive Drawing Table, Human-AI Interaction, Generative Model, Edvard Munch, Visual Aesthetics",

author = "Christian Sivertsen and Ren{\'e} Haas and Jensen, {Halfdan Hauch} and L{\o}vlie, {Anders Sundnes}",

year = "2023",

month = apr,

day = "19",

doi = "10.1145/3544549.3583902",

language = "English",

pages = "1--5",

booktitle = "CHI EA '23",

publisher = "Association for Computing Machinery",

address = "United States",

}

Exploring a Digital Art Collection through Drawing Interactions with a Deep Generative Model. / Sivertsen, Christian; Haas, René; Jensen, Halfdan Hauch et al.
CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2023. p. 1-5 451.

Research output: Conference Article in Proceeding or Book/Report chapter › Conference abstract in proceedings › Research

TY - ABST

T1 - Exploring a Digital Art Collection through Drawing Interactions with a Deep Generative Model

AU - Sivertsen, Christian

AU - Haas, René

AU - Jensen, Halfdan Hauch

AU - Løvlie, Anders Sundnes

PY - 2023/4/19

Y1 - 2023/4/19

N2 - New Snow is an interactive drawing table that investigates human interaction with a deep generative model based on Edvard Munch’s sketching practice. Through drawings with pen and paper, the user can interact with the model which will return synthetic sketches based on the input drawings in real time. The model is a reflection of the training data, and it is thus constrained to representing images within the latent space of Edvard Munch’s sketching practice. As the user familiarizes themselves with the model it allows them to become sensitized to the visual aesthetic belonging to this practice. This potential for familiarization with the aesthetic of a dataset via the model has implications for human-AI interaction and non-verbal art mediation.

AB - New Snow is an interactive drawing table that investigates human interaction with a deep generative model based on Edvard Munch’s sketching practice. Through drawings with pen and paper, the user can interact with the model which will return synthetic sketches based on the input drawings in real time. The model is a reflection of the training data, and it is thus constrained to representing images within the latent space of Edvard Munch’s sketching practice. As the user familiarizes themselves with the model it allows them to become sensitized to the visual aesthetic belonging to this practice. This potential for familiarization with the aesthetic of a dataset via the model has implications for human-AI interaction and non-verbal art mediation.

KW - Interactive Drawing Table

KW - Human-AI Interaction

KW - Generative Model

KW - Edvard Munch

KW - Visual Aesthetics

U2 - 10.1145/3544549.3583902

DO - 10.1145/3544549.3583902

M3 - Conference abstract in proceedings

SP - 1

EP - 5

BT - CHI EA '23

PB - Association for Computing Machinery

ER -

Exploring a Digital Art Collection through Drawing Interactions with a Deep Generative Model

Abstract

Keywords

Access to Document

Fingerprint

Cite this