ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues  

作　　者：Ho Yin Au Jie Chen Junkun Jiang Yike Guo 

机构地区：[1]Department of Computer Science,Hong Kong Baptist University,Hong Kong 999077,China [2]Department of Computer Science and Engineering,The Hong Kong University of Science and Engineering,Hong Kong 999077,China

出　　处：《Machine Intelligence Research》2024年第4期771-781,共11页机器智能研究（英文版）

基　　金：supported by the Theme-based Research Scheme,Research Grants Council of Hong Kong,China(T45-205/21-N).

摘　　要：To generate dance that temporally and aesthetically matches the music is a challenging problem in three aspects.First,the generated motion should be beats-aligned to the local musical features.Second,the global aesthetic style should be matched between motion and music.And third,the generated motion should be diverse and non-self-repeating.To address these challenges,we propose ReChoreoNet,which re-choreographs high-quality dance motion for a given piece of music.A data-driven learning strategy is proposed to efficiently correlate the temporal connections between music and motion in a progressively learned cross-modality embedding space.The beats-aligned content motion will be subsequently used as autoregressive context and control signal to control a normalizing-flow model,which transfers the style of a prototype motion to the final generated dance.In addition,we present an aesthetically labelled music-dance repertoire(MDR)for both efficient learning of the cross-modality embedding,and understanding of the aesthetic connections between music and motion.We demonstrate that our repertoire-based framework is robustly extensible in both content and style.Both quantitative and qualitative experiments have been carried out to validate the efficiency of our proposed model.

关 键 词：Generative model cross-modality learning normalizing flow tempo synchronization style transfer. 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]