SyncMos：面向多智能体场景交互的可扩展运动同步
SyncMos: Scalable Motion Synchronisation for Multi-Agent Scene Interaction
把扩散后验采样与时间规整控制结合，在无需重训练的前提下把单智能体运动合成模型扩展为多智能体时序同步生成，可直接迁移到人体-场景交互、虚拟角色动画等需要跨主体时序对齐的生成任务。
原文依据 Our synchronisation module, built upon time-warping control and diffusion posterior sampling, aligns interaction timing across agents without retraining.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维场景中文本引导的运动生成推动了人体-场景交互合成的发展，为具身智能、场景理解与虚拟智能体仿真提供了支撑。尽管近期研究已开始探索多智能体场景，但在多个智能体之间实现时序同步的交互仍是一个开放挑战。现有方法在处理多样化的交互情境时，往往在灵活性与可扩展性上存在局限。本文提出一种方法，借助单一智能体的运动合成模型实现同步的多智能体交互，其核心由两个组件构成：文本引导的依赖感知故事规划器与时序同步模块。故事规划器将自然语言指令解析为带有时间依赖关系的结构化事件序列。我们的同步模块建立在时间规整控制与扩散后验采样之上，无需重新训练即可对齐各智能体之间的交互时序。实验结果表明，所提框架能够有效建模事件之间的时间依赖与因果顺序。在多种交互类型上的评估显示，该方法改善了时序对齐，并能生成与文本指令一致、连贯的多智能体运动。
英文原文摘要 1240 字符
Text-guided motion generation in 3D scenes has advanced the synthesis of human-scene interactions, contributing to embodied AI, scene understanding, and virtual agent simulation. While recent studies have begun exploring multi-agent scenarios, achieving temporally synchronised interactions among multiple agents remains an open challenge. Existing methods are often limited in flexibility and scalability when handling diverse interaction contexts.We present a method that enables synchronised multi-agent interaction using a single-agent motion synthesis model through two key components: a text-guided dependency-aware story planner and a temporal synchronisation module. The story planner interprets natural language instructions into structured event sequences with temporal dependencies. Our synchronisation module, built upon time-warping control and diffusion posterior sampling, aligns interaction timing across agents without retraining.Experimental results demonstrate that the proposed framework effectively models temporal dependencies and causal order between events. Evaluations across diverse interaction types show improved temporal alignment and coherent multi-agent motion generation consistent with textual instructions.