The physical properties of an object, such as mass, significantly affect how we manipulate it with our hands. Surprisingly, this aspect has so far been neglected in prior work on 3D motion synthesis. To improve the naturalness of the synthesized 3D hand object motions, this work proposes MACS the first MAss Conditioned 3D hand and object motion Synthesis approach. Our approach is based on cascaded diffusion models and generates interactions that plausibly adjust based on the object mass and interaction type. MACS also accepts a manually drawn 3D object trajectory as input and synthesizes the natural 3D hand motions conditioned by the object mass. This flexibility enables MACS to be used for various downstream applications, such as generating synthetic training data for ML tasks, fast animation of hands for graphics workflows, and generating character interactions for computer games. We show experimentally that a small-scale dataset is sufficient for MACS to reasonably generalize across interpolated and extrapolated object masses unseen during the training. Furthermore, MACS shows moderate generalization to unseen objects, thanks to the mass-conditioned contact labels generated by our surface contact synthesis model ConNet. Our comprehensive user study confirms that the synthesized 3D hand-object interactions are highly plausible and realistic.

翻译：物体的物理属性（如质量）显著影响我们用手操控物体的方式。然而令人惊讶的是，这一方面在之前的3D运动合成研究中一直被忽略。为提升合成3D手部物体运动的自然性，本文提出MACS——首个基于质量条件化的3D手部与物体运动合成方法。该方法基于级联扩散模型，能够根据物体质量和交互类型生成合理调整的交互动作。MACS还可接受人工绘制的3D物体轨迹作为输入，合成由物体质量条件化的自然3D手部运动。这种灵活性使MACS能应用于多种下游任务，例如为机器学习任务生成合成训练数据、为图形工作流快速生成手部动画，以及为电脑游戏生成角色交互。实验表明，小规模数据集足以使MACS能够合理泛化至训练中未见过的插值与外推物体质量。此外，得益于我们的表面接触合成模型ConNet生成的质量条件化接触标签，MACS对未见物体展现了中等程度的泛化能力。综合用户研究证实，其合成的3D手部物体交互动作具有高度的真实性与合理性。