用指尖先验分步生成钢琴手部动作，更真实自然。
Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors
- 分四阶段生成：先定指尖位置，再优化轨迹，后估手腕，最后合成姿态。
- 在FürElise数据集上F1达0.910，远超扩散模型的0.121。
- 适合音乐生成、动作捕捉与人机交互研究者参考。
生成逼真的钢琴手部动作需要兼顾精确性与自然性。基于物理的方法精度高但动作僵硬；数据驱动模型虽自然，却难保证位置准确。钢琴动作具有天然层次：给定琴键布局与指法，指尖位置几乎确定，而手腕及中间关节则具风格自由度。本文提出四阶段框架，利用这一层次结构：(1) 基于统计的指尖定位，(2) FiLM条件化轨迹优化，(3) 手腕估计，(4) 基于STGCN的姿态合成。我们贡献了专家标注指法的FürElise数据集（153首曲目，约10小时）。实验表明F1=0.910，显著优于扩散基线（F1=0.121），用户研究（N=41）确认生成质量接近动捕水平。专业钢琴家评估（N=5）指出前瞻动作仍是主要差距，为未来改进提供明确方向。
原文摘要 · Abstract (English)
Synthesizing realistic piano hand motions requires both precision and naturalness. Physics-based methods achieve precision but produce stiff motions; data-driven models learn natural dynamics but struggle with positional accuracy. Piano motion exhibits a natural hierarchy: fingertip positions are nearly deterministic given piano geometry and fingering, while wrist and intermediate joints offer stylistic freedom. We present [OURS], a four-stage framework exploiting this hierarchy: (1) statistics-based fingertip positioning, (2) FiLM-conditioned trajectory refinement, (3) wrist estimation, and (4) STGCN-based pose synthesis. We contribute expert-annotated fingerings for the FürElise dataset (153 pieces, ~10 hours). Experiments demonstrate F1 = 0.910, substantially outperforming diffusion baselines (F1 = 0.121), with user study (N=41) confirming quality approaching motion capture. Expert evaluation by professional pianists (N=5) identified anticipatory motion as the key remaining gap, providing concrete directions for future improvement.
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。