用少量采样步数实现高效高质3D舞蹈生成，兼顾物理合理与艺术表现。
FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
- 采用均值流结合物理约束，仅需几步采样即可生成高质量动作。
- 在AIST++和FineDance数据集上同时达到顶尖运动质量与生成效率。
- 支持交互式编辑，适合虚拟现实与数字娱乐场景使用。
音乐到舞蹈生成旨在将听觉信号转化为富有表现力的人体运动，广泛应用于虚拟现实、编舞设计和数字娱乐。尽管已有进展，现有方法生成效率有限，难以支撑高保真3D渲染，制约了真实应用中角色的表现力。为此，我们提出FlowerDance，不仅生成兼具物理合理性与艺术表现力的精细动作，还显著提升推理速度与内存利用率。具体而言，FlowerDance结合均值流（MeanFlow）与物理一致性约束，仅用少数采样步骤即可实现高质量运动生成。此外，其采用基于BiMamba的轻量骨干网络与通道级跨模态融合结构，以非自回归方式高效生成舞蹈。同时支持运动编辑，用户可交互式优化舞蹈序列。在AIST++和FineDance数据集上的大量实验表明，FlowerDance在运动质量和生成效率方面均达当前最优水平。代码将在录用后开源。
原文摘要 · Abstract (English)
Music-to-dance generation aims to translate auditory signals into expressive human motion, with broad applications in virtual reality, choreography, and digital entertainment. Despite promising progress, the limited generation efficiency of existing methods leaves insufficient computational headroom for high-fidelity 3D rendering, thereby constraining the expressiveness of 3D characters during real-world applications. Thus, we propose FlowerDance, which not only generates refined motion with physical plausibility and artistic expressiveness, but also achieves significant generation efficiency on inference speed and memory utilization. Specifically, FlowerDance combines MeanFlow with Physical Consistency Constraints, which enables high-quality motion generation with only a few sampling steps. Moreover, FlowerDance leverages a simple but efficient model architecture with BiMamba-based backbone and Channel-Level Cross-Modal Fusion, which generates dance with efficient non-autoregressive manner. Meanwhile, FlowerDance supports motion editing, enabling users to interactively refine dance sequences. Extensive experiments on AIST++ and FineDance show that FlowerDance achieves state-of-the-art results in both motion quality and generation efficiency. Code will be released upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。