J. Imaging, Volume 10, Issue 7 (July 2024) – 24 articles
Cover Story (view full-size image):
As most of Da Vinci’s artworks depict young and beautiful women, this study investigates the ability of generative models to create human portraits in the style of Da Vinci across different social categorizations. We begin by evaluating vector representations in the latent space of the portraits to maximize the subject's preserved facial features and conclude that sparser vectors have a greater effect on key identity features. To objectively evaluate and quantify the trade-off between identity and style, this paper also presents the results of a survey of human feedback. The analysis of which showed a high tolerance for the loss of key identity features in the resulting portraits when the Da Vinci style is more pronounced, with some exceptions including African individuals. View this paper
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
- You may sign up for e-mail alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Previous Issue
Next Issue
