Beauty and the Beat: Music‐Driven Choral Conducting With Beat‐Aware Diffusion

Music‐driven motion generation has attracted increasing attention, yet conducting remains underexplored despite its central role in musical communication. We address this gap with a focus on choral conducting. We introduce Maestro3D, a large‐scale 3D dataset of professional performances, and propose a beat‐aware diffusion framework enhanced by a novel phase‐based beat representation that explicitly encodes rhythmic structure. Both quantitative and qualitative evaluations show that our approach achieves superior accuracy, realism, and synchronization compared to existing methods.