DanceDuo: Bridging Human Movement and AI Choreography

📅 2026-06-24
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work proposes an interactive AI choreography system based on diffusion models to generate dance motions synchronized with multi-style music and enable intuitive visual comparison between user-uploaded videos and AI-generated dances. It represents the first application of diffusion models to music-driven, multi-genre dance generation, integrating human pose estimation for precise motion alignment and visual analysis. The system offers customizable options including music selection, virtual avatars, and an interactive interface. User studies indicate that the interface is user-friendly and the comparison functionality is practical, demonstrating strong potential for both entertainment and professional dance training applications.
📝 Abstract
In recent years, advancements in deep learning and generative models have revolutionized music-driven dance generation. This paper introduces a novel platform, namely DanceDuo, leveraging diffusion models to generate AI-choreographed dance sequences synchronized with a variety of music genres, to encourage dancing practice. The system allows users to interact with AI by selecting music tracks, humanoid models, and importing personal dance videos for comparison, fostering a rich and engaging user experience. DanceDuo not only offers dance generation but also integrates human pose estimation models to provide users with insightful comparisons of their own performances with AI-generated sequences. We conducted a comprehensive user study, revealing that users found the interface intuitive, with particular praise for the dance comparison feature. Our DanceDuo contributes significantly to the integration of AI in dance choreography, offering novel avenues for both recreational and professional applications.
Problem

Research questions and friction points this paper is trying to address.

dance generation
music synchronization
AI choreography
human pose comparison
interactive dance platform
Innovation

Methods, ideas, or system contributions that make the work stand out.

diffusion models
music-driven dance generation
human pose estimation
AI choreography
interactive dance platform
🔎 Similar Papers
No similar papers found.
G
Gia-Cat Bui-Le
University of Science, VNU-HCM, Ho Chi Minh City, Vietnam; Vietnam National University, Ho Chi Minh City, Vietnam
T
Tuong-Vy Truong-Thuy
University of Science, VNU-HCM, Ho Chi Minh City, Vietnam; Vietnam National University, Ho Chi Minh City, Vietnam
H
Hai-Dang Nguyen
University of Science, VNU-HCM, Ho Chi Minh City, Vietnam; Vietnam National University, Ho Chi Minh City, Vietnam
Trung-Nghia Le
Trung-Nghia Le
University of Science, VNU-HCM
Applied Deep LearningApplied Computer VisionMultimedia Security