• Trans-
• /
• v.12
• /
• pp.1-19
• /
• 2022

This study predicts and raises the changes that AI will bring to dance art when machine-based choreography began, and finds questions we can ask as human artists. Research suggests that one of the crises of dance in the era of machine creative arts is that artificial intelligence does not stay in the tool of human choreography but becomes the subject of choreography. It is based on the political discourse of choreography that artificial intelligence has the power to control and restrict human dancers. This comes from a sense of crisis that the AI takes over the area of choreography and the human choreographer remains an incompetent coordinator, and as a result, the dancer's dancing body can be reduced to a mechanical body controlled by AI. In order for these concerns not to become a reality, this study proposes three measures. First, choreographer and dancer should develop digital literacy to live in the age of AI art. Secondly, choreographer should acquire the ability to accurately distinguish the roles of human choreographer, dancer, and AI in creative work. Thirdly, various levels of discourse on AI dance should be formed by actively conducting mutual media research of dance and technology. Through these efforts, the human dancer will exist as a subject of art, not a passive agent in the new dance ecosystem brought by the innovation of artificial intelligence technology and will be able to face an era coexistence with artificial intelligence creativily and productively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.544-545
• /
• 2023

최근 화제인 가상 아이돌의 춤 제작에 많은 자원 및 비용이 발생한다. 만일 춤을 자동으로 생성해 3D 모델에 피팅하면 이러한 비용을 줄일 수 있으며, 다양하고 복잡한 춤의 구현도 가능할 것이다. 또한, 댄스 게임을 통해 춤을 배우고 즐기는 사람들이 많지만, 경험할 수 있는 춤이 한정적이며, 모션 인식 정확도가 낮다는 단점이 있다. 따라서 본 논문에서는 트랜스포머 구조의 인공지능 모델을 통해 음악에 어울리는 3D 춤 모션을 자동으로 생성하고, 3D 자세 추정 모델을 사용해 사용자의 모션을 추정한 후, 두 모션의 유사도를 랜드마크 3D 좌표로 계산하여 판정하고자 한다. 이는 1 인 댄스 룸 또는 댄스 게임에 활용되어 발전 가능하다.