Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces MoSAIC, a latent diffusion framework designed for part-local reference-conditioned motion style transfer, which addresses the challenge of editing character motion while preserving essential aspects of the original action. By employing aligned intervention supervision, the framework constructs synchronized references and counterfactual targets through controlled local transformations, allowing for precise routing of user-selected references to specific body parts. The results show a significant reduction in preserved-region error and off-target leakage, alongside improved selected-target response, highlighting MoSAIC's effectiveness in enhancing the trade-off between response and preservation in motion editing tasks.
Aligned intervention supervision in MoSAIC achieves a remarkable reduction in motion editing errors while enhancing the responsiveness of selected body parts.
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.