TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography

TL;DR

TCDiff++ is an advanced diffusion model that generates harmonious, long-duration group dance choreography driven by music, effectively addressing collision, foot sliding, and abrupt transitions for realistic dance synthesis.

Contribution

The paper introduces TCDiff++, a novel end-to-end framework with new embedding and loss techniques to improve long-duration, collision-free, and foot-sliding minimized group dance generation.

Findings

Achieves state-of-the-art results in long-duration dance generation

Effectively reduces dancer collisions and foot sliding

Produces coherent and high-quality group choreography

Abstract

Music-driven dance generation has garnered significant attention due to its wide range of industrial applications, particularly in the creation of group choreography. During the group dance generation process, however, most existing methods still face three primary issues: multi-dancer collisions, single-dancer foot sliding and abrupt swapping in the generation of long group dance. In this paper, we propose TCDiff++, a music-driven end-to-end framework designed to generate harmonious group dance. Specifically, to mitigate multi-dancer collisions, we utilize a dancer positioning embedding to encode temporal and identity information. Additionally, we incorporate a distance-consistency loss to ensure that inter-dancer distances remain within plausible ranges. To address the issue of single-dancer foot sliding, we introduce a swap mode embedding to indicate dancer swapping patterns and design a Footwork Adaptor to refine raw motion, thereby minimizing foot sliding. For long group dance generation, we present a long group diffusion sampling strategy that reduces abrupt position shifts by injecting positional information into the noisy input. Furthermore, we integrate a Sequence Decoder layer to enhance the model's ability to selectively process long sequences. Extensive experiments demonstrate that our TCDiff++ achieves state-of-the-art performance, particularly in long-duration scenarios, ensuring high-quality and coherent group dance generation.