Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel

Sugiura, Keiya; Ogawa, Toshio; Adachi, Yoshitaka; Sun, Fei; Suzuki, Asuka; Yamanaka, Akinori; Nakada, Nobuo; Ishimoto, Takuya; Nakano, Takayoshi; Koizumi, Yuichiro

doi:https://doi.org/10.3390/jimaging9050090

Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel

Sugiura, Keiya; Ogawa, Toshio; Adachi, Yoshitaka et al.

Journal of Imaging, 2023, 9(5), 90

Number of Access:847（2025-08-21 06:21 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/93116

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
JImaging_9_5	pdf	None	11.7 MB	55	2023.11.14

Creative Commons : Attribution

Item Information

Output File Export EndNote Basic Export Mendeley

Title	Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel
Creator	CreatorName Sugiura, Keiya
	NRID 1000010708910 1000010708910 CreatorName Ogawa, Toshio
	NRID 1000090370311 1000090370311 CreatorName Adachi, Yoshitaka
	NRID 1000000836562 1000000836562 CreatorName Sun, Fei
	NRID 1000090802603 1000090802603 CreatorName Suzuki, Asuka
	NRID 1000050542198 1000050542198 CreatorName Yamanaka, Akinori
	NRID 1000050380580 1000050380580 CreatorName Nakada, Nobuo
	NRID 1000050508835 1000050508835 CreatorName Ishimoto, Takuya
	NRID 1000030243182 1000030243182 ORCID 0000-0001-8052-1698 0000-0001-8052-1698 researchmap permalink read0013987 read0013987 Scopus Author ID 7403896013 7403896013 CreatorName Nakano, Takayoshi
	NRID 1000010322174 1000010322174 ORCID 0000-0001-7061-7135 0000-0001-7061-7135 researchmap permalink YuichiroKoizumi YuichiroKoizumi Scopus Author ID 57202772340 57202772340 CreatorName Koizumi, Yuichiro
Subject	additive manufacturing
	autocorrelation function
	generative adversarial network
	SliceGAN
	synthetic 3D image
Description	Sugiura K., Ogawa T., Adachi Y., et al. Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel. Journal of Imaging 9, 90 (2023); https://doi.org/10.3390/jimaging9050090.
Abstract	A modified SliceGAN architecture was proposed to generate a high-quality synthetic three-dimensional (3D) microstructure image of TYPE 316L material manufactured through additive methods. The quality of the resulting 3D image was evaluated using an auto-correlation function, and it was discovered that maintaining a high resolution while doubling the training image size was crucial in creating a more realistic synthetic 3D image. To meet this requirement, modified 3D image generator and critic architecture was developed within the SliceGAN framework.
Publisher	MDPI
Source Title	Journal of Imaging
Volume (Issue)	9(5)
Page	90
Date of Issued	2023-04-29
Language	English
Handle URL	https://hdl.handle.net/11094/93116
eISSN	2313433X
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.3390/jimaging9050090
Access Rights	open access
CopyRight	This article is licensed under a Creative Commons Attribution 4.0 International License.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCMI Type	Text
DCTERMS.bibliographicCitation	Journal of Imaging. 2023, 9(5), p. 90
DC.title	Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel
DC.creator	Sugiura, Keiya
	Ogawa, Toshio
	Adachi, Yoshitaka
	Sun, Fei
	Suzuki, Asuka
	Yamanaka, Akinori
	Nakada, Nobuo
	Ishimoto, Takuya
	Nakano, Takayoshi
	Koizumi, Yuichiro
DC.publisher	MDPI
DC.language' scheme='DCTERMS.RFC1766	English
DC.type' scheme='DCTERMS.DCMIType	Text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2023-04-29
DC.identifier	https://doi.org/10.3390/jimaging9050090
DC.subject	additive manufacturing
	autocorrelation function
	generative adversarial network
	SliceGAN
	synthetic 3D image
DC.description	Sugiura K., Ogawa T., Adachi Y., et al. Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel. Journal of Imaging 9, 90 (2023); https://doi.org/10.3390/jimaging9050090.
DCTERMS.abstract	A modified SliceGAN architecture was proposed to generate a high-quality synthetic three-dimensional (3D) microstructure image of TYPE 316L material manufactured through additive methods. The quality of the resulting 3D image was evaluated using an auto-correlation function, and it was discovered that maintaining a high resolution while doubling the training image size was crucial in creating a more realistic synthetic 3D image. To meet this requirement, modified 3D image generator and critic architecture was developed within the SliceGAN framework.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	93116
citation_title	Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel
citation_author	Sugiura, Keiya
	Ogawa, Toshio
	Adachi, Yoshitaka
	Sun, Fei
	Suzuki, Asuka
	Yamanaka, Akinori
	Nakada, Nobuo
	Ishimoto, Takuya
	Nakano, Takayoshi
	Koizumi, Yuichiro
citation_publisher	MDPI
citation_language	English
citation_date	2023-04-29
citation_journal_title	Journal of Imaging
citation_volume	9
citation_issue	5
citation_firstpage	90
citation_doi	https://doi.org/10.3390/jimaging9050090
citation_public_url	https://hdl.handle.net/11094/93116

Big-Volume SliceGAN for Improving a Synthetic 3D Microstructure Image of Additive-Manufactured TYPE 316L Steel

Link to primary information

Item Information

Show details