Evolving neural style transfer blends

Simon Colton

doi:10.1007/978-3-030-72914-1_5

Evolving neural style transfer blends

Simon Colton

Department of Human Centred Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

Neural style transfer is an image filtering technique used in both digital art practice and commercial software. We investigate blending the styles afforded by neural models via interpolation and overlaying different stylisations. In order to produce preset stylisation filters for the development of a casual creator app, we experiment with various MAP-Elites quality/diversity approaches to evolving style transfer blends with particular properties, while maintaining diversity in the population.

Original language	English
Title of host publication	10th International Conference, EvoMUSART 2021 Held as Part of EvoStar 2021 Virtual Event, April 7–9, 2021 Proceedings
Editors	Juan Romero, Tiago Martins, Nereida Rodríguez-Fernández
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	65-81
Number of pages	17
ISBN (Electronic)	9783030729141
ISBN (Print)	9783030729134
DOIs	https://doi.org/10.1007/978-3-030-72914-1_5
Publication status	Published - 2021
Event	International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design 2021 - Online, Virtual, Online, Spain Duration: 7 Apr 2021 → 9 Apr 2021 Conference number: 10th https://link.springer.com/book/10.1007/978-3-030-72914-1 (Proceedings) http://www.evostar.org/2021/evomusart/ (Website)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	12693
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design 2021
Abbreviated title	EvoMUSART 2021
Country/Territory	Spain
City	Virtual, Online
Period	7/04/21 → 9/04/21
Internet address	https://link.springer.com/book/10.1007/978-3-030-72914-1 (Proceedings) http://www.evostar.org/2021/evomusart/ (Website)

Keywords

Casual creators
MAP-Elites
Neural style transfer

Access to Document

10.1007/978-3-030-72914-1_5

Cite this

@inproceedings{798accc4abe1420586ff2cc3dabf7b7d,

title = "Evolving neural style transfer blends",

abstract = "Neural style transfer is an image filtering technique used in both digital art practice and commercial software. We investigate blending the styles afforded by neural models via interpolation and overlaying different stylisations. In order to produce preset stylisation filters for the development of a casual creator app, we experiment with various MAP-Elites quality/diversity approaches to evolving style transfer blends with particular properties, while maintaining diversity in the population.",

keywords = "Casual creators, MAP-Elites, Neural style transfer",

author = "Simon Colton",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design 2021, EvoMUSART 2021 ; Conference date: 07-04-2021 Through 09-04-2021",

year = "2021",

doi = "10.1007/978-3-030-72914-1_5",

language = "English",

isbn = "9783030729134",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "65--81",

editor = "Juan Romero and Tiago Martins and Nereida Rodr{\'i}guez-Fern{\'a}ndez",

booktitle = "10th International Conference, EvoMUSART 2021 Held as Part of EvoStar 2021 Virtual Event, April 7–9, 2021 Proceedings",

url = "https://link.springer.com/book/10.1007/978-3-030-72914-1, http://www.evostar.org/2021/evomusart/",

}

Colton, S 2021, Evolving neural style transfer blends. in J Romero, T Martins & N Rodríguez-Fernández (eds), 10th International Conference, EvoMUSART 2021 Held as Part of EvoStar 2021 Virtual Event, April 7–9, 2021 Proceedings. Lecture Notes in Computer Science, vol. 12693, Springer, Cham Switzerland, pp. 65-81, International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design 2021, Virtual, Online, Spain, 7/04/21. https://doi.org/10.1007/978-3-030-72914-1_5

Evolving neural style transfer blends. / Colton, Simon.

10th International Conference, EvoMUSART 2021 Held as Part of EvoStar 2021 Virtual Event, April 7–9, 2021 Proceedings. ed. / Juan Romero; Tiago Martins; Nereida Rodríguez-Fernández. Cham Switzerland : Springer, 2021. p. 65-81 (Lecture Notes in Computer Science; Vol. 12693).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Evolving neural style transfer blends

AU - Colton, Simon

N1 - Conference code: 10th

PY - 2021

Y1 - 2021

N2 - Neural style transfer is an image filtering technique used in both digital art practice and commercial software. We investigate blending the styles afforded by neural models via interpolation and overlaying different stylisations. In order to produce preset stylisation filters for the development of a casual creator app, we experiment with various MAP-Elites quality/diversity approaches to evolving style transfer blends with particular properties, while maintaining diversity in the population.

AB - Neural style transfer is an image filtering technique used in both digital art practice and commercial software. We investigate blending the styles afforded by neural models via interpolation and overlaying different stylisations. In order to produce preset stylisation filters for the development of a casual creator app, we experiment with various MAP-Elites quality/diversity approaches to evolving style transfer blends with particular properties, while maintaining diversity in the population.

KW - Casual creators

KW - MAP-Elites

KW - Neural style transfer

UR - http://www.scopus.com/inward/record.url?scp=85107421878&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-72914-1_5

DO - 10.1007/978-3-030-72914-1_5

M3 - Conference Paper

AN - SCOPUS:85107421878

SN - 9783030729134

T3 - Lecture Notes in Computer Science

SP - 65

EP - 81

BT - 10th International Conference, EvoMUSART 2021 Held as Part of EvoStar 2021 Virtual Event, April 7–9, 2021 Proceedings

A2 - Romero, Juan

A2 - Martins, Tiago

A2 - Rodríguez-Fernández, Nereida

PB - Springer

CY - Cham Switzerland

T2 - International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design 2021

Y2 - 7 April 2021 through 9 April 2021

ER -

Evolving neural style transfer blends

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this