We present a method to animate a character incorporating multiple part-wise motion priors (PMP). While previous works allow creating realistic articulated motions from reference data, the range of motion is largely limited by the available samples. Especially for the interaction-rich scenarios, it is impractical to attempt acquiring every possible interacting motion, as the combination of physical parameters increases exponentially. The proposed PMP allows us to assemble multiple part skills to animate a character, creating a diverse set of motions with different combinations of existing data. In our pipeline, we can train an agent with a wide range of part-wise priors. Therefore, each body part can obtain a kinematic insight of the style from the motion captures, or at the same time extract dynamics-related information from the additional part-specific simulation. For example, we can first train a general interaction skill, e.g. grasping, only for the dexterous part, and then combine the expert trajectories from the pre-trained agent with the kinematic priors of other limbs. Eventually, our whole-body agent learns a novel physical interaction skill even with the absence of the object trajectories in the reference motion sequence.

翻译：我们提出一种方法，通过整合多个部位级运动先验（Part-wise Motion Priors, PMP）来驱动角色动画。虽然以往的工作允许从参考数据中生成逼真的关节运动，但运动范围很大程度上受限于可用样本。尤其是在交互丰富的场景中，试图获取每一种可能的交互运动是不切实际的，因为物理参数的组合数量呈指数级增长。所提出的PMP使我们能够组合多个部位技能来驱动角色，从而利用现有数据的不同组合生成多样化的运动集。在我们的流程中，可训练一个具备广泛部位级先验的智能体。因此，每个身体部位既能从动作捕捉中获取运动学层面的风格洞察，又能同时从额外的部位专属仿真中提取动力学相关信息。例如，我们可首先仅针对灵巧部位训练通用交互技能（如抓取），然后将预训练智能体生成的专家轨迹与其他肢体的运动学先验相结合。最终，即使参考运动序列中缺失物体轨迹，我们的全身智能体仍能习得全新的物理交互技能。