We propose Lodge++, a choreography framework to generate high-quality, ultra-long, and vivid dances given the music and desired genre. To handle the challenges in computational efficiency, the learning of complex and vivid global choreography patterns, and the physical quality of local dance movements, Lodge++ adopts a two-stage strategy to produce dances from coarse to fine. In the first stage, a global choreography network is designed to generate coarse-grained dance primitives that capture complex global choreography patterns. In the second stage, guided by these dance primitives, a primitive-based dance diffusion model is proposed to further generate high-quality, long-sequence dances in parallel, faithfully adhering to the complex choreography patterns. Additionally, to improve the physical plausibility, Lodge++ employs a penetration guidance module to resolve character self-penetration, a foot refinement module to optimize foot-ground contact, and a multi-genre discriminator to maintain genre consistency throughout the dance. Lodge++ is validated by extensive experiments, which show that our method can rapidly generate ultra-long dances suitable for various dance genres, ensuring well-organized global choreography patterns and high-quality local motion.

翻译：我们提出Lodge++，一种根据音乐和指定舞蹈风格生成高质量、超长且生动的舞蹈动作的编舞框架。为应对计算效率、复杂生动的全局编舞模式学习以及局部舞蹈动作物理质量等挑战，Lodge++采用从粗到精的两阶段策略生成舞蹈。在第一阶段，全局编舞网络通过生成粗粒度舞蹈基元来捕捉复杂的全局编舞模式。在第二阶段，基于这些舞蹈基元的引导，我们提出基于基元的舞蹈扩散模型，以并行方式进一步生成高质量的长序列舞蹈，并忠实遵循复杂的编舞模式。此外，为提升物理合理性，Lodge++采用穿透引导模块解决角色自穿透问题，足部优化模块改善足部与地面接触，以及多风格判别器确保舞蹈全程的风格一致性。大量实验验证表明，Lodge++能快速生成适用于多种舞蹈风格的超长舞蹈序列，同时保证组织有序的全局编舞模式和高质量的局部动作。