Exploring Aesthetic Experience through Intended Technical Imperfection in AI-Based Interactive Media Art; [AI 기반 인터렉티브 미디어아트에서 의도된 기술적 불완전성 으로 인한 관객의 미적 경험 연구]

Abstract

Background Artificial intelligence (AI) has emerged as a powerful new tool for artistic creation, particularly within technologically driven fields such as interactive media art. However, most applications of AI tend to focus on technical perfection and accurate reproduction, often limiting the diversity of artistic expression. This study aims to move beyond this tendency by exploring the potential of intentional technical imperfection as a condition for expanding artistic value and aesthetic experience. Methods This study utilized AnimateDiff, an AI video generation model based on Stable Diffusion, and intentionally induced visual distortions by adjusting parameters such as Sampling Step, CFG scale, and Control Weight. Through this process, an AI-based interactive media art piece generating visually ambiguous yet familiar forms was created. Designed to allow audiences to engage with real-time visual transformations, the work was evaluated through survey-based assessments and interviews to collect and analyze viewers’ aesthetic experiences. Results In this context, AI’s intended imperfection functioned not as mere error or failure, but as an experiential condition that enabled artistic serendipity and interpretive openness. Unpredictable visual distortions were associated with emotional immersion and stimulated the audience’s aesthetic imagination. Viewers tended to interpret these imperfect outputs in novel ways, which in turn fostered active engagement and participation. Conclusions This study suggests that technical imperfection in AI-based artistic creation can function as a design element that conditionally activates aesthetic experience, rather than as a flaw to be eliminated. By shifting the focus from technical completeness to experience-oriented design, this research differentiates itself from prior AI art studies centered on precision or output fidelity. It proposes the possibility of reimagining imperfection as an artistic asset and contributes to the experimental expansion of interactive media art. © This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/), which permits unrestricted educational and non-commercial use, provided the original work is properly cited.