シラキ　シノ   Shiraki Shino   白木　詩乃    所属   千葉工業大学  情報変革科学部 情報工学科    職種   助教
発行・発表の年月	2026/03
形態種別	学術雑誌
標題	Image quality enhancement of directional volumetric displays using generative adversarial networks
執筆形態	共著
掲載誌名	Optics Continuum
掲載区分	国外
出版社・発行元	Optica Publishing Group
巻・号・頁	5(3),902-902頁
著者・共著者	Mitsuru Baba,Shino Shiraki,Hirotaka Nakayama,Tomoyoshi Shimobaba,Tomoyoshi Ito,Atsushi Shiraki
概要	We propose a voxel optimization model utilizing generative adversarial networks for directional volumetric displays, in which the image displayed depends on the observation direction. Employing the L1 loss, learned perceptual image patch similarity (LPIPS), and adversarial losses, the proposed generator overcomes the limitation of the conventional iterative approximation method, which minimizes only pixel-wise errors. When evaluated on 40,670 image pairs from the Microsoft Common Objects in Context 2017 dataset, the generator demonstrated quantitative improvements over the conventional method, with an LPIPS of 0.1415 and a Fréchet inception distance of 5.654 (versus 0.1487 and 6.381, respectively, in the conventional method). Furthermore, visual comparisons indicated that the proposed approach mitigated the horizontal linear artifacts observed in images generated by the conventional method.
DOI	10.1364/optcon.590589
ISSN	/2770-0208
PermalinkURL	https://opg.optica.org/viewmedia.cfm?URI=optcon-5-3-902&seq=0