通过接触矩阵建模舞蹈互动，提升双人舞动作生成的精确性与同步性。
Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling
- 分阶段设计：先用体部独立编码器增强表征，再用接触感知扩散模型生成动作与交互关系。
- 在双人舞数据上实现更低的FID_k（8.89）和更高的BED（0.4606），交互更真实、节奏更同步。
- 适合研究动作生成、人机交互或舞蹈动画的开发者，尤其关注精细互动建模场景。
生成真实反应式动作（一方对另一方固定动作做出反应）极具挑战，因交互约束严格且可行解空间有限。本文聚焦双人舞场景，该场景高质量数据稀缺，动作模式复杂，人体交互细节丰富且精巧。为此，提出两阶段新框架：第一阶段引入分体部编码器的运动VQ-VAE，结合联合解码器，在解码时动态建模各身体部位间依赖关系，避免生成动作不一致；第二阶段提出接触感知扩散模型，联合生成动作与个体间的接触矩阵，显式建模交互关系，并在采样过程中提供精准的约束引导。实验表明，本方法在杜尔兰多（Duolando）基础上显著提升性能，FID_k为8.89（原25.30），FID_cd为8.01（原9.97），BED达0.4606（原0.2858），表明交互保真度与节奏同步性均获改善。
原文摘要 · Abstract (English)
Generating realistic reactive motions, in which one person reacts to the fixed motions of others, is challenging due to strict interaction constraints and a limited feasible solution space. This paper focuses on a typical scenario: duet dance, where high-quality data is scarce, motion patterns are complex, and the details of human interactions are both intricate and abundant. To tackle these challenges, we propose a novel two-stage framework. In the first stage, we introduce a motion VQ-VAE with separate body-part encoders and a joint decoder, enabling specialized codebooks to enhance representation capacity while dynamically modeling dependencies across body parts during decoding, thereby preventing inconsistencies in the generated motions. In the second stage, we propose a contact-aware diffusion model for reactive motion generation that jointly generates motion and a contact matrix between individuals, enabling explicit interaction modeling and providing guidance toward more precise and constrained interaction dynamics during sampling. Experiments show that our method outperforms Duolando with lower $\text{FID}_k$ (8.89 vs. 25.30) and $\text{FID}_{cd}$ (8.01 vs. 9.97), as well as a higher BED (0.4606 vs. 0.2858), indicating improved interaction fidelity and rhythmic synchronization.
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。