We address the problem of generating 3D human motions in dyadic activities. In contrast to the concurrent works, which mainly focus on generating the motion of a single actor from the textual description, we generate the motion of one of the actors from the motion of the other participating actor in the action. This is a particularly challenging, under-explored problem, that requires learning intricate relationships between the motion of two actors participating in an action and also identifying the action from the motion of one actor. To address these, we propose partner conditioned motion operator (PaCMO), a neural operator-based generative model which learns the distribution of human motion conditioned by the partner's motion in function spaces through adversarial training. Our model can handle long unlabeled action sequences at arbitrary time resolution. We also introduce the "Functional Frechet Inception Distance" ($F^2ID$) metric for capturing similarity between real and generated data for function spaces. We test PaCMO on NTU RGB+D and DuetDance datasets and our model produces realistic results evidenced by the $F^2ID$ score and the conducted user study.
翻译:我们处理在三角活动中产生3D人类运动的问题。与同时进行的工作相比,我们主要侧重于从文字描述中产生单一行动者的运动,我们从行动的其他参与行动者的动作中产生一个行动者的运动。这是一个特别具有挑战性、探索不足的问题,需要学习两个行动者参与一项行动的动作之间的复杂关系,并且从一个行动者的动作中确定行动的行动。为了解决这些问题,我们提议以伙伴为条件的运动操作员(PACMO)为主的神经操作员基因化模型,通过对抗性训练学习以伙伴在功能空间中运动为条件的人类运动的分布。我们的模型可以在任意的解答中处理长期未标记的行动序列。我们还采用“Functional Frechetepeption距离”(F2ID$)衡量标准,以获取功能空间实际数据和生成的数据之间的相似性。我们用NTU RGB+D和DitDance数据集测试PACMO,我们的模型产生现实的结果,以$F2ID$的分数和用户研究为证明。