DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax
For researchers in text-driven motion generation, this work provides a new dataset and framework that significantly improves fine-grained controllability over complex dance sequences.
DanceCrafter tackles fine-grained text-driven controllable dance generation by introducing Choreographic Syntax, a theoretical framework with an annotation system, and DanceFlow, a dataset of 41 hours of motion with 6.34 million words of descriptions. The model achieves state-of-the-art performance in motion quality, controllability, and naturalness.
Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent difficulty of articulating complex choreographies. Characterizing dance is particularly challenging owing to its intricate spatial dynamics, strong directionality, and the highly decoupled movements of distinct body parts. To overcome these bottlenecks, we bridge principles from dance studies, human anatomy, and biomechanics to propose \textit{Choreographic Syntax}, a novel theoretical framework with a tailored annotation system. Grounded in this syntax, we combine professional dance archives with high-fidelity motion capture data to construct \textbf{DanceFlow}, the most fine-grained dance dataset to date. It encompasses 41 hours of high-quality motions paired with 6.34 million words of detailed descriptions. At the model level, we introduce \textbf{DanceCrafter}, a tailored motion transformer built upon the Momentum Human Rig. To circumvent optimization instabilities, we construct a continuous manifold motion representation paired with a hybrid normalization strategy. Furthermore, we design an anatomy-aware loss to explicitly regulate the decoupled nature of body parts. Together, these adaptations empower DanceCrafter to achieve the high-fidelity and stable generation of complex dance sequences. Extensive evaluations and user studies demonstrate our state-of-the-art performance in motion quality, fine-grained controllability, and generation naturalness.