Melola Discovery

← Melola Discovery

Journal

Development of Double-Tail Generative Adversarial Network with Adaptive Style Transfer for Anime Background Production with Makoto Shinkai's Stylization

Scientific Journal of Informatics · Vol. 12 No. 1 (2025) · pp. 159–170

DOI
10.15294/sji.v12i1.20850
ISSN
2407-7658, 2460-0040
Published
2025-06-06
Publisher
Universitas Negeri Semarang
Language
eng

Abstract

Purpose: Traditionally, 2D anime production involves the expertise of experienced animators and is labor-intensive and time-consuming. Generative adversarial networks (GANs) have been developed to create high-quality anime over the years. However, the developed GANs still have caveats, such as the presence of artifacts, high-frequency noise, color and semantic structure mismatches, blurring, and texture issues. Additionally, research on AI-generated anime images with a particular style is still lacking. Thus, this study aimed to develop double-tail generative adversarial network (DTGAN) with adaptive style transfer to generate quality anime background images aligning with Makoto Shinkai's anime style. Methods: A dataset of real world and anime images was collected and preprocessed. The training was run, and an inference process was done to generate background images with the anime style of Makoto Shinkai using DTGAN with adaptive style transfer. Evaluations of the images produced were performed using visual comparison and quantitative analysis using Fréchet Inception Distance (FID) and peak signal-to-noise ratio (PSNR). Result: Compared to other methods, the images generated by DTGAN with adaptive style transfer had the lowest FID and highest PSNR values of.38.7 and 19.4 dB, respectively. Visual comparison of the images against other methods and real anime image of Makoto Shinkai demonstrated that images from DTGAN had the best quality that matched Makoto's style, as observed from color, background preservation, photorealistic style, and light contrast. Novelty: These findings suggest that DTGAN with adaptive style transfer using adaptive instance normalization (AdaIN) and linearly adaptive denormalization (LADE) outperforms other methods, highlighting its practical use for 2D anime production.

Keywords

Collaboration network of the authors

40 authors · 79 co-authorship links · 16 across different organisations · showing the 40 most connected

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universitas Amikom Yogyakarta
  • Universitas Gadjah Mada
  • Universidad de Murcia
  • Universitas AKPRIND Indonesia
  • Politeknik Perkapalan Negeri Surabaya
  • Hellenic Open University
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Hery WinarsiAffiliation unknown5
Arief SetyantoUniversitas Amikom Yogyakarta5
Anggit Dwi HartantoUniversitas Amikom Yogyakarta4
KusriniAffiliation unknown4
Ahmad Fikri IskandarUniversitas Amikom Yogyakarta3
Wahyu HidayatUniversitas Amikom Yogyakarta3
I Made Artha AgastyaUniversitas Amikom Yogyakarta3
Rodrigo Martínez‐BéjarUniversidad de Murcia2
Erwin SyahrudinUniversitas Amikom Yogyakarta2
Siwi Pramatama Mars WijayantiAffiliation unknown2
Arif JumariAffiliation unknown2
Witri Wahyu LestariAffiliation unknown2
Fitria RahmawatiAffiliation unknown2
Andi SunyotoUniversitas Amikom Yogyakarta2
Mardi Siswo UtomoAffiliation unknown2
Catur Riyono Heri WibowoUniversitas Amikom Yogyakarta1
HanafiAffiliation unknown1
Agung Budi PrasetioUniversitas Amikom Yogyakarta1
Mursyid ArdiansyahUniversitas Amikom Yogyakarta1
Suwanto RaharjoUniversitas AKPRIND Indonesia1
Agung Budi PrasetyoPoliteknik Perkapalan Negeri Surabaya1
Risna SariUniversitas Amikom Yogyakarta1
Tonny HidayatUniversitas Amikom Yogyakarta1
Theofanis G. OrphanoudakisHellenic Open University1
Ariel Yonatan AlinUniversitas Amikom Yogyakarta1
Kumara Ari YuanaUniversitas Amikom Yogyakarta1
Retzi Yosia LewuAffiliation unknown1
Ainul YaqinUniversitas Amikom Yogyakarta1
Kartikasari Kusuma AgustiningsihUniversitas Amikom Yogyakarta1
Muhammad Altoumi AlsyaibaniUniversitas Amikom Yogyakarta1
Agus HarjokoUniversitas Gadjah Mada1
Retantyo WardoyoUniversitas Gadjah Mada1
Sri T. HartatiUniversitas Gadjah Mada1
Mei KurniawanAffiliation unknown1
M. SuyantoAffiliation unknown1
Aiman MukhlishahAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/sji/oai, first harvested 6 Nov 2026, last seen 8 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Development of Double-Tail Generative Adversarial Network with Adaptive Style Transfer for Anime Background Production with Makoto Shinkai's Stylization</dc:title>
	<dc:creator xml:lang="en">Purwanto, Agus</dc:creator>
	<dc:creator xml:lang="en">Kusrini, Kusrini</dc:creator>
	<dc:creator xml:lang="en">Utami, Ema</dc:creator>
	<dc:creator xml:lang="en">Agustriawan, David</dc:creator>
	<dc:subject xml:lang="en">Double-tail generative adversarial network</dc:subject>
	<dc:subject xml:lang="en">Anime background production</dc:subject>
	<dc:subject xml:lang="en">AdaIN</dc:subject>
	<dc:subject xml:lang="en">LADE</dc:subject>
	<dc:subject xml:lang="en">Makoto shinkai</dc:subject>
	<dc:description xml:lang="en">Purpose: Traditionally, 2D anime production involves the expertise of experienced animators and is labor-intensive and time-consuming. Generative adversarial networks (GANs) have been developed to create high-quality anime over the years. However, the developed GANs still have caveats, such as the presence of artifacts, high-frequency noise, color and semantic structure mismatches, blurring, and texture issues. Additionally, research on AI-generated anime images with a particular style is still lacking. Thus, this study aimed to develop double-tail generative adversarial network (DTGAN) with adaptive style transfer to generate quality anime background images aligning with Makoto Shinkai's anime style.
Methods: A dataset of real world and anime images was collected and preprocessed. The training was run, and an inference process was done to generate background images with the anime style of Makoto Shinkai using DTGAN with adaptive style transfer. Evaluations of the images produced were performed using visual comparison and quantitative analysis using Fréchet Inception Distance (FID) and peak signal-to-noise ratio (PSNR).
Result: Compared to other methods, the images generated by DTGAN with adaptive style transfer had the lowest FID and highest PSNR values of.38.7 and 19.4 dB, respectively. Visual comparison of the images against other methods and real anime image of Makoto Shinkai demonstrated that images from DTGAN had the best quality that matched Makoto's style, as observed from color, background preservation, photorealistic style, and light contrast.
Novelty: These findings suggest that DTGAN with adaptive style transfer using adaptive instance normalization (AdaIN) and linearly adaptive denormalization (LADE) outperforms other methods, highlighting its practical use for 2D anime production.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2025-06-06</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/sji/article/view/20850</dc:identifier>
	<dc:identifier>10.15294/sji.v12i1.20850</dc:identifier>
	<dc:source xml:lang="en">Scientific Journal of Informatics; Vol. 12 No. 1: Regular Issue; 159-170</dc:source>
	<dc:source>2407-7658</dc:source>
	<dc:source>2460-0040</dc:source>
	<dc:source>10.15294/sji.v12i1</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/sji/article/view/20850/4346</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2025 Scientific Journal of Informatics</dc:rights>
</oai_dc:dc>