用动态系统视角对齐多模态生物力学数据，提升运动生成质量。
Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment
- 在扩散过程每一步对齐不同模态的局部潜在流形。
- 相比单模态生成，多模态联合建模提升动作还原精度。
- 适合研究人体运动建模与假肢/康复系统设计者。
我们提出一种基于动力学系统视角的跨模态生物力学运动生成互对齐扩散框架。将观测到的关节角度（X）和地面反作用力（Y）视为共享运动动力学系统的互补观测，通过在扩散过程中对齐各模态的潜在表示，使一种模态能帮助去噪和消除另一种的歧义。该方法的核心思想是：同一时间窗口内的X与Y反映相同的动态系统相位，因此可共享潜在流形。我们引入一种简单的局部潜在流形对齐（LLMA）策略，在潜在空间中融合一阶与二阶对齐机制，实现无需复杂结构的鲁棒跨模态生物力学生成。在多模态人体生物力学数据上的实验表明，跨模态局部潜在动态对齐显著提升了生成保真度，并获得更优表征。
原文摘要 · Abstract (English)
We present a mutually aligned diffusion framework for cross-modal biomechanical motion generation, guided by a dynamical systems perspective. By treating each modality, e.g., observed joint angles ($X$) and ground reaction forces ($Y$), as complementary observations of a shared underlying locomotor dynamical system, our method aligns latent representations at each diffusion step, so that one modality can help denoise and disambiguate the other. Our alignment approach is motivated by the fact that local time windows of $X$ and $Y$ represent the same phase of an underlying dynamical system, thereby benefiting from a shared latent manifold. We introduce a simple local latent manifold alignment (LLMA) strategy that incorporates first-order and second-order alignment within the latent space for robust cross-modal biomechanical generation without bells and whistles. Through experiments on multimodal human biomechanics data, we show that aligning local latent dynamics across modalities improves generation fidelity and yields better representations.
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。