发表机构
Nanyang Technological University; KTH Royal Institute of Technology; Lancaster University（南洋理工大学; 瑞典皇家理工学院; 兰卡斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TAME提出拓扑约束骨骼传播与编辑聚焦表示对齐的流匹配变换器，实现异构人体骨骼上的文本驱动运动编辑，在MotionFix和TopoMotionFix上优于现有方法。
AI 中文摘要
文本驱动的运动编辑根据文本指令修改现有运动序列，同时保留源运动的内容。现有方法通常针对单一、固定的骨骼拓扑构建，这限制了它们在角色关节数量和骨骼层级不同的动画流水线中的使用。我们提出了拓扑感知运动编辑器（TAME），一种流匹配变换器，可在拓扑各异的人体骨骼上编辑运动。TAME将运动表示为每个关节、每帧的令牌，并通过骨骼、时间和文本交叉注意力层建模关节间、帧间以及与文本指令的交互。为使骨骼注意力遵循每个角色的层级，TAME用拓扑约束骨骼传播（TCSP）取代全关节注意力，该机制将注意力限制在骨骼邻接矩阵中的一跳运动学邻居上。我们进一步引入编辑聚焦表示对齐（EFRA），一种自蒸馏表示对齐策略，仅在编辑相关的关节-时间令牌上将学生特征与更干净的EMA教师特征对齐，使编辑忠实于指令。为使该设置可训练且可比较，我们构建了TopoMotionFix，一个MotionFix的多拓扑扩展，包含可见和不可见拓扑评估协议。TAME在MotionFix上的编辑对齐和源保留方面优于先前方法，并在TopoMotionFix中可靠地编辑不可见骨骼上的运动。
英文摘要
Text-driven motion editing modifies an existing motion sequence according to a text instruction while preserving the content of the source motion. Existing methods are typically built for a single, fixed skeletal topology, which limits their use in animation pipelines where characters differ in joint count and skeletal hierarchy. We present Topology-Aware Motion Editor (TAME), a flow-matching transformer that edits motions on humanoid skeletons of varying topology. TAME represents motion as per-joint, per-frame tokens and models interactions among joints, across frames, and with the text instruction through skeletal, temporal, and text cross-attention layers. To make the skeletal attention follow each character's hierarchy, TAME replaces full joint attention with Topology-Constrained Skeletal Propagation (TCSP), which restricts attention to one-hop kinematic neighbors in the skeleton's adjacency matrix. We further introduce Edit-Focused Representation Alignment (EFRA), a self-distilled representation alignment strategy that aligns student features with cleaner EMA-teacher features exclusively on edit-relevant joint-time tokens, making edits faithful to the instruction. To make this setting trainable and comparable, we construct TopoMotionFix, a multi-topology extension of MotionFix with seen- and unseen-topology evaluation protocols. TAME outperforms previous methods in edit alignment and source preservation on MotionFix and reliably edits motions on unseen skeletons in TopoMotionFix.
