Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence
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 sign...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845784/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575583040569344 |
|---|---|
| author | Tomas Eglynas Dovydas Lizdenis Aistis Raudys Sergej Jakovlev Miroslav Voznak |
| author_facet | Tomas Eglynas Dovydas Lizdenis Aistis Raudys Sergej Jakovlev Miroslav Voznak |
| author_sort | Tomas Eglynas |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-516c0b3c2029471cb40bcc6a5fe00342 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-516c0b3c2029471cb40bcc6a5fe003422025-01-31T23:04:39ZengIEEEIEEE Access2169-35362025-01-0113195881959710.1109/ACCESS.2025.353172610845784Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial IntelligenceTomas Eglynas0https://orcid.org/0000-0002-9973-5896Dovydas Lizdenis1Aistis Raudys2https://orcid.org/0000-0002-0139-6014Sergej Jakovlev3Miroslav Voznak4https://orcid.org/0000-0001-5135-7980Marine Research Institute, Klaipeda University, Klaipėda, LithuaniaMarine Research Institute, Klaipeda University, Klaipėda, LithuaniaFaculty of Mathematics and Informatics, Vilnius University, Vilnius, LithuaniaMarine Research Institute, Klaipeda University, Klaipėda, LithuaniaMarine Research Institute, Klaipeda University, Klaipėda, LithuaniaNeural 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.https://ieeexplore.ieee.org/document/10845784/Human image synthesisimage processingcomputer graphicsvisualizationphotorealism |
| spellingShingle | Tomas Eglynas Dovydas Lizdenis Aistis Raudys Sergej Jakovlev Miroslav Voznak Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence IEEE Access Human image synthesis image processing computer graphics visualization photorealism |
| title | Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence |
| title_full | Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence |
| title_fullStr | Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence |
| title_full_unstemmed | Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence |
| title_short | Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence |
| title_sort | exploring generative adversarial networks comparative analysis of facial image synthesis and the extension of creative capacities in artificial intelligence |
| topic | Human image synthesis image processing computer graphics visualization photorealism |
| url | https://ieeexplore.ieee.org/document/10845784/ |
| work_keys_str_mv | AT tomaseglynas exploringgenerativeadversarialnetworkscomparativeanalysisoffacialimagesynthesisandtheextensionofcreativecapacitiesinartificialintelligence AT dovydaslizdenis exploringgenerativeadversarialnetworkscomparativeanalysisoffacialimagesynthesisandtheextensionofcreativecapacitiesinartificialintelligence AT aistisraudys exploringgenerativeadversarialnetworkscomparativeanalysisoffacialimagesynthesisandtheextensionofcreativecapacitiesinartificialintelligence AT sergejjakovlev exploringgenerativeadversarialnetworkscomparativeanalysisoffacialimagesynthesisandtheextensionofcreativecapacitiesinartificialintelligence AT miroslavvoznak exploringgenerativeadversarialnetworkscomparativeanalysisoffacialimagesynthesisandtheextensionofcreativecapacitiesinartificialintelligence |