Global Position Aware Group Choreography using Large Language Model
This addresses the problem of generating synchronized multi-person dances for applications in entertainment or animation, representing a novel but incremental advance in a relatively unexplored area.
The paper tackles group dance generation by modeling it as a sequence-to-sequence translation task using a fine-tuned Large Language Model, achieving state-of-the-art performance with realistic, diverse dances that maintain music correlation and dancer consistency.
Dance serves as a profound and universal expression of human culture, conveying emotions and stories through movements synchronized with music. Although some current works have achieved satisfactory results in the task of single-person dance generation, the field of multi-person dance generation remains relatively novel. In this work, we present a group choreography framework that leverages recent advancements in Large Language Models (LLM) by modeling the group dance generation problem as a sequence-to-sequence translation task. Our framework consists of a tokenizer that transforms continuous features into discrete tokens, and an LLM that is fine-tuned to predict motion tokens given the audio tokens. We show that by proper tokenization of input modalities and careful design of the LLM training strategies, our framework can generate realistic and diverse group dances while maintaining strong music correlation and dancer-wise consistency. Extensive experiments and evaluations demonstrate that our framework achieves state-of-the-art performance.