[论文] FlowMoP: Stochastic Multi-Person Motion Prediction

论文概要

研究领域: CV 作者: Aadya Agrawal, Ho Kei Cheng, Alexander Schwing 发布时间: 2026-11-06 arXiv: 2611.09882

中文摘要

预测多人的未来运动本质上是随机的：相同的观测历史因意图、协调和社交语境的不同而允许多种合理的延续。然而，多人3D运动预测的主流范式仍是确定性的——现有方法为每个智能体产生固定数量的输出。本文提出条件流匹配框架 FlowMoP，联合为多个智能体生成多样化的未来运动，同时建模全局轨迹和根相对姿态。B样条重参数化压缩生成状态空间并强制时间平滑性，双流 Transformer 使每个智能体的预测以观测到的邻居运动为条件实现交互感知预测。该方法在 CMU-Mocap (UMPM) 和 3DPW 上达到最先进性能，在关节位置误差、姿态误差和最终位移误差上均超越确定性基线——尽管产生的是完整预测分布。作者还在 WorldPose（大规模职业足球数据集）上建立了首个运动预测基线，其中社交条件化明显将预测不确定性集中到受交互约束的方向上。

原文摘要

Predicting the future motion of multiple people is inherently stochastic: the same observed history admits many plausible continuations depending on intent, coordination, and social context. Yet the dominant paradigm in multi-person 3D motion prediction remains deterministic, with existing methods producing a fixed number of outputs per agent. In contrast, we present a conditional flow matching framework that jointly generates diverse future motions for multiple agents, modeling both global trajectories and root-relative poses. A B-spline reparameterization compresses the generative state space while enforcing temporal smoothness, and a dual-stream transformer conditions each agent's predictions on observed neighbor motion for interaction-aware forecasting. Our method achieves state-of-the...

#论文 #arXiv #CV #小凯