Bridging Ancient Art and Modern Technology: AI-Driven Storytelling of Dunhuang Mogao Grottoes

Open Access
Article
Conference Proceedings
Authors: Yang LiuXinran MaoJiexin SunJiayi QianSibei ChenCherine Abigail KurniawanClement Fernando KusumaFang Liu

Abstract: Artificial intelligence (AI) is rapidly transforming creative design, raising critical questions about its role as a collaborator rather than a replacement for human creativity. This project investigates human–AI co-creation in the digital preservation and storytelling of the Dunhuang Mogao Grottoes, a UNESCO World Heritage site and a pivotal crossroads of Silk Road civilizations. Facing accelerating threats from environmental degradation and mass tourism, the Grottoes require preservation strategies that move beyond static digital archiving toward dynamic cultural revitalization.Positioning AI as an active creative partner, the study explores how artists train and guide Artificial Intelligence–Generated Content (AIGC) systems to interpret and reimagine the iconography and narratives of the Mogao murals. Through iterative collaboration, AI contributes visual variations and motion design, while human expertise ensures historical context, aesthetic judgment, and narrative coherence. The outcome is a high-quality moving-image sequence that fuses AI-generated visuals with human-centered storytelling, transforming ancient Buddhist parables into immersive digital experiences.Beyond offering an innovative model for heritage conservation and audience engagement, this research advances discourse in digital media arts by demonstrating how AI can amplify, rather than replace, human creativity. By bridging ancient art with cutting-edge technology, the project proposes a scalable framework for integrating AI-driven production into the preservation of cultural heritage and contemporary digital storytelling.

Keywords: Dunhuang, Mogao Grottoes, Artificial Intelligence, Immersive Storytelling, Cultural heritage preservation, Interactive narratives

DOI: 10.54941/ahfe1007078

Cite this paper:

Downloads
1
Visits
2
Download