A new article “Toward Unbiased High-Quality Portraits through Latent-Space Evaluation” is published on MDPI by Doaa Almhaithawi 1, Alessandro Bellini 2 and Tania Cerquitelli 1.

Images, texts, voices, and signals can be synthesized by latent spaces in a multidimensional vector, which can be explored without the hurdles of noise or other interfering factors. In this paper, we present a practical use case that demonstrates the power of latent space in exploring complex realities such as image space. We focus on DaVinciFace, an AI-based system that explores the StyleGAN2 space to create a high-quality portrait for anyone in the style of the Renaissance genius Leonardo da Vinci…

Read more: https://www.mdpi.com/2313-433X/10/7/157



1 Department of Control and Computer Engineering, Politecnico di Torino, 10129 Torino, Italy
2 Prime Lab, Mathema s.r.l., 50142 Florence, Italy

Related Post