This study presents a case of AR content creation that expands traditional printed images into digital content using generative artificial intelligence (AI) and augmented reality (AR). Ttakjibon cover images, characterized by strong color contrast and...
This study presents a case of AR content creation that expands traditional printed images into digital content using generative artificial intelligence (AI) and augmented reality (AR). Ttakjibon cover images, characterized by strong color contrast and figure-centered composition, were selected as visual materials. Using a generative AI-based video synthesis tool, Studio D-ID, the cover images were transformed into video content. During this process, character videos combining dialogues and voice elements associated with the original images were generated. The resulting videos were integrated into an image-based AR environment developed with Unity, enabling AI-generated videos to be augmented and played when target images are recognized in a mobile setting. This study focuses on analyzing the content production process and implementation cases, demonstrating that the integration of generative AI and AR technologies can serve as a practical production approach for extending static visual images into interactive digital content.