arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.19692cs.CV
收藏

Interact2Ar:通过自回归扩散模型生成全身体态的人与人交互

Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models

Universidad de Alicante(阿利坎特大学);Universitat de Barcelona and Computer Vision Center(巴塞罗那大学与计算机视觉中心);Imperial College London(伦敦帝国理工学院)

Pablo Ruiz-Ponce, Sergio Escalera, José García-Rodríguez, Jiankang Deng, Rolandos Alexandros Potamias

AI总结:

本文提出Interact2Ar,首个基于文本条件的自回归扩散模型,用于生成全身体态的人与人交互,通过专用并行分支实现详细手部运动,结合新颖的记忆技术提升适应性,支持多场景应用。

摘要:

生成逼真的人与人交互是具有挑战性的任务,需要高质量的个体身体和手部运动以及所有参与者的协调性。由于可用数据限制和学习复杂性增加,先前方法往往忽略手部运动,限制了交互的真实性和表达性。此外,当前基于扩散的方法同时生成整个运动序列,限制了其捕捉人类交互反应和适应性能力。为了解决这些限制,我们引入Interact2Ar,首个端到端的文本条件自回归扩散模型,用于生成全身体态的人与人交互。Interact2Ar通过专用并行分支整合详细手部运动学,实现高保真的全身体态生成。此外,我们引入一个自回归管道,结合一种新的记忆技术,利用高效的大型上下文窗口来适应人类交互的内在变异性。模型的适应性支持一系列下游应用,包括时间运动合成、实时适应干扰以及扩展到多人场景。为了验证生成的运动,我们引入了一组稳健的评估者和扩展的度量标准,专门用于评估全身体态交互。通过定量和定性实验,我们展示了Interact2Ar的最先进的性能。

英文摘要:

Generating realistic human-human interactions is a challenging task that requires not only high-quality individual body and hand motions, but also coherent coordination among all interactants. Due to limitations in available data and increased learning complexity, previous methods tend to ignore hand motions, limiting the realism and expressivity of the interactions. Additionally, current diffusion-based approaches generate entire motion sequences simultaneously, limiting their ability to capture the reactive and adaptive nature of human interactions. To address these limitations, we introduce Interact2Ar, the first end-to-end text-conditioned autoregressive diffusion model for generating full-body, human-human interactions. Interact2Ar incorporates detailed hand kinematics through dedicated parallel branches, enabling high-fidelity full-body generation. Furthermore, we introduce an autoregressive pipeline coupled with a novel memory technique that facilitates adaptation to the inherent variability of human interactions using efficient large context windows. The adaptability of our model enables a series of downstream applications, including temporal motion composition, real-time adaptation to disturbances, and extension beyond dyadic to multi-person scenarios. To validate the generated motions, we introduce a set of robust evaluators and extended metrics designed specifically for assessing full-body interactions. Through quantitative and qualitative experiments, we demonstrate the state-of-the-art performance of Interact2Ar.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑