GANS for realistic animation: A qualitative study using ATLAS.ti.

Saved in:

Bibliographic Details
Title:	GANS for realistic animation: A qualitative study using ATLAS.ti.
Authors:	Wibowo, Mars Caroline¹ caroline@stekom.ac.id, Nugroho, Aris Sarwo¹, Purhita, Edy Jogatama¹
Source:	Journal of Graphic Engineering & Design (JGED). Jun2026, Vol. 17 Issue 2, p1-9. 9p.
Subjects:	Generative adversarial networks, Realism in motion pictures, Qualitative research, Composition (Art)
Abstract:	This study aims to explore the effectiveness of GANs in generating animations that achieve high levels of realism, focusing on motion quality, texture detail, visual composition, and frame-to-frame coherence. A qualitative approach was employed using ATLAS.ti to analyze outputs from models such as MoCo-GAN and StyleGAN3. The dataset included 110 animations, from which key visual elements were coded and analyzed thematically. The findings reveal that 68% of the animations demonstrated smooth motion transitions, while 20% exhibited jerky movements and 12% contained motion artifacts. Similarly, 70% of the animations featured highly detailed textures, but 20% had flat backgrounds, and 10% showed lighting inconsistencies. Visual compositions with strategic framing and depth perception were observed in 55% and 30% of the animations, respectively, whereas only 15% maintained symmetrical layouts. These results underscore the strengths and limitations of GANs in achieving realism, particularly in complex scenarios. This study contributes to the growing body of literature on GAN applications in animation by identifying critical visual factors that enhance aesthetic and narrative coherence. Practical implications include guiding designers and developers in leveraging GANs for high-quality animation production. Future research is recommended to address existing technical challenges and evaluate audience responses to GAN-generated animations, paving the way for more dynamic and engaging visual content. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Graphic Engineering & Design (JGED) is the property of Journal of Graphic Engineering & Design (JGED) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	This study aims to explore the effectiveness of GANs in generating animations that achieve high levels of realism, focusing on motion quality, texture detail, visual composition, and frame-to-frame coherence. A qualitative approach was employed using ATLAS.ti to analyze outputs from models such as MoCo-GAN and StyleGAN3. The dataset included 110 animations, from which key visual elements were coded and analyzed thematically. The findings reveal that 68% of the animations demonstrated smooth motion transitions, while 20% exhibited jerky movements and 12% contained motion artifacts. Similarly, 70% of the animations featured highly detailed textures, but 20% had flat backgrounds, and 10% showed lighting inconsistencies. Visual compositions with strategic framing and depth perception were observed in 55% and 30% of the animations, respectively, whereas only 15% maintained symmetrical layouts. These results underscore the strengths and limitations of GANs in achieving realism, particularly in complex scenarios. This study contributes to the growing body of literature on GAN applications in animation by identifying critical visual factors that enhance aesthetic and narrative coherence. Practical implications include guiding designers and developers in leveraging GANs for high-quality animation production. Future research is recommended to address existing technical challenges and evaluate audience responses to GAN-generated animations, paving the way for more dynamic and engaging visual content. [ABSTRACT FROM AUTHOR]
ISSN:	2217379X