无需对应的在线人体运动重定向
Correspondence-free online human motion retargeting
AI总结：
本文提出无需形状与时间对应的无监督在线人体运动重定向框架，融合几何感知变形与骨骼感知迁移，在两个数据集上达到SOTA并可泛化至新运动和体型。
摘要：
我们提出了一种用于无监督人体运动重定向的数据驱动框架，该框架利用源主体的运动为目标主体制作动画。我们的方法无需对应关系，既不需要源形状与目标形状之间的空间对应，也不需要源运动不同帧之间的时间对应。这使得可以用任意运动中的人体序列来为目标形状制作动画，这些序列可能由4D采集平台或消费级设备捕获。我们的方法统一了两类现有工作的优势，即利用长期时间上下文的骨骼运动重定向，以及保留表面细节的基于表面的重定向，具体方式是将几何感知变形模型与骨骼感知运动迁移方法相结合。这使得方法能够在考虑长期时间上下文的同时兼顾表面细节。在推理期间，我们的方法在线运行，即输入可以按串行方式处理，并且重定向在每帧仅需一次前向传播即可完成。实验表明，在训练期间纳入长期时间上下文可以提高该方法在骨骼运动和细节保留方面的准确性。此外，我们的方法可泛化到未观测过的运动和身体形状。我们证明，该方法在两个测试数据集上取得了最先进的结果，并且可用于利用多视角采集平台的输出为人体模型制作动画。代码可在\url{https://gitlab.inria.fr/rrekikdi/human-motion-retargeting2023}获取。
英文摘要：
We present a data-driven framework for unsupervised human motion retargeting that animates a target subject with the motion of a source subject. Our method is correspondence-free, requiring neither spatial correspondences between the source and target shapes nor temporal correspondences between different frames of the source motion. This allows to animate a target shape with arbitrary sequences of humans in motion, possibly captured using 4D acquisition platforms or consumer devices. Our method unifies the advantages of two existing lines of work, namely skeletal motion retargeting, which leverages long-term temporal context, and surface-based retargeting, which preserves surface details, by combining a geometry-aware deformation model with a skeleton-aware motion transfer approach. This allows to take into account long-term temporal context while accounting for surface details. During inference, our method runs online, i.e. input can be processed in a serial way, and retargeting is performed in a single forward pass per frame. Experiments show that including long-term temporal context during training improves the method's accuracy for skeletal motion and detail preservation. Furthermore, our method generalizes to unobserved motions and body shapes. We demonstrate that our method achieves state-of-the-art results on two test datasets and that it can be used to animate human models with the output of a multi-view acquisition platform. Code is available at \url{https://gitlab.inria.fr/rrekikdi/human-motion-retargeting2023}.
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。
