发表机构
The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MoSAIC是一种局部部位参考条件动作风格迁移的潜在扩散框架，通过对齐干预监督优化响应与保留的权衡，在评估中降低了误差并提升了选中区域响应与路由影响浓度。
AI 中文摘要
编辑角色动作时，通常需要从一个或多个参考动作中迁移手势或步态，同时保留源动作、时序、根轨迹及未选中的身体区域。然而，现有动作数据集很少为任意局部部位内容-参考组合提供配对目标，而自重构训练可能让扩散模型复现内容动作，却未充分利用路由参考。我们提出MoSAIC，一种用于局部部位参考条件动作风格迁移的潜在扩散框架。MoSAIC按解剖区域分解内容与参考特征，通过单独的条件通路保留根轨迹，并将用户选中的参考路由至单个身体部位。其核心贡献是对齐干预监督，该方法通过受控局部变换构建同步参考与反事实目标，使训练期间可直接观测到请求的区域响应与需保留的动作。在包含128个动作和896种路由条件的冻结评估中，与全身路由相比，局部部位掩码路由将保留区域误差从70.64mm降至66.45mm，匹配噪声的脱靶泄漏从18.08mm降至9.88mm，同时保持了选中区域的正向响应。匹配预算的延续研究进一步显示，保留对齐干预监督可使选中目标响应相对提升8.8%，请求路由影响浓度提升2.0个百分点。这些结果表明，MoSAIC改善了选择性可控局部部位动作编辑所需的响应-保留权衡。
英文摘要
Editing character motion often requires transferring a gesture or gait from one or more reference motions while preserving the source action, timing, root trajectory, and unselected body regions. Existing motion datasets, however, rarely provide paired targets for arbitrary part-local content--reference combinations, and self-reconstruction training may allow a diffusion model to reproduce the content motion while underusing the routed reference. We present MoSAIC, a latent diffusion framework for part-local reference-conditioned motion style transfer. MoSAIC factorizes content and reference features by anatomical region, preserves the root trajectory through a separate conditioning pathway, and routes user-selected references to individual body parts. Its central contribution is aligned intervention supervision, which constructs synchronized references and counterfactual targets through controlled local transformations, making both the requested regional response and the motion to be preserved directly observable during training. In a frozen evaluation comprising 128 motions and 896 routed conditions, part-masked routing reduces preserved-region error from 70.64 to 66.45~mm and matched-noise off-target leakage from 18.08 to 9.88~mm relative to whole-body routing, while retaining a positive selected-region response. A matched-budget continuation study further shows that retaining aligned intervention supervision produces an 8.8\% relative increase in selected-target response and a 2.0-percentage-point increase in requested-route influence concentration. These results demonstrate that MoSAIC improves the response--preservation trade-off required for selective and controllable part-local motion editing.
Comments23 pages, 6 figures, 11 tables. Project page: https://utsa-virlab.github.io/MoSAIC/
