Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence

作     者：Eglynas, Tomas Lizdenis, Dovydas Raudys, Aistis Jakovlev, Sergej Voznak, Miroslav 

作者机构：Klaipeda Univ Marine Res Inst LT-92294 Klaipeda Lithuania Vilnius Univ Fac Math & Informat LT-03225 Vilnius Lithuania VSB Tech Univ Ostrava Telecommun Dept Ostrava 70833 Czech Republic 

出 版 物：《IEEE ACCESS》 (IEEE Access)

年 卷 期：2025年第13卷

页      面：19588-19597页

核心收录：

基　　金：European Union (EU) within the REFRESH Project-Research Excellence for Region Sustainability and High-Tech Industries of the European Just Transition Fund [CZ.10.03.01/00/22_003/0000048] Ministry of Education, Youth, and Sports of Czech Republic (MEYS CZ) within a Student Grant Competition in the VSB-Technical University of Ostrava [SGS SP2024/061] 

主　　题：Generative adversarial networks Generators Training Faces Noise Synthetic data Data models Loss measurement Decoding Computational modeling Human image synthesis image processing computer graphics visualization photorealism 

摘      要：Neural networks have become foundational in modern technology, driving advancements across diverse domains such as medicine, law enforcement, and information technology. By enabling algorithms to learn from data and perform tasks autonomously, they eliminate the need for explicit programming. A significant challenge in this field is replicating the uniquely human capacity for creativity-envisioning and realizing novel concepts and tangible creations. Generative Adversarial Networks (GANs), a leading approach in this effort, are especially notable for synthesizing realistic human facial images. Despite the success of GANs, comprehensive comparative studies of face-generating GAN methodologies are limited. This paper addresses this gap by analyzing the scope and capabilities of facial generation, detailing the principles of the original GAN framework, and reviewing prominent GAN variants specifically designed for facial synthesis. Through performance evaluations and fidelity analysis of generated images, this study contributes to a deeper understanding of GAN potential in advancing artificial intelligence creativity through performance evaluations and fidelity analysis of generated images.