Motion retargeting is a fundamental problem in computer graphics and computer vision. Existing approaches usually have many strict requirements, such as the source-target skeletons needing to have the same number of joints or share the same topology. To tackle this problem, we note that skeletons with different structure may have some common body parts despite the differences in joint numbers. Following this observation, we propose a novel, flexible motion retargeting framework. The key idea of our method is to regard the body part as the basic retargeting unit rather than directly retargeting the whole body motion. To enhance the spatial modeling capability of the motion encoder, we introduce a pose-aware attention network (PAN) in the motion encoding phase. The PAN is pose-aware since it can dynamically predict the joint weights within each body part based on the input pose, and then construct a shared latent space for each body part by feature pooling. Extensive experiments show that our approach can generate better motion retargeting results both qualitatively and quantitatively than state-of-the-art methods. Moreover, we also show that our framework can generate reasonable results even for a more challenging retargeting scenario, like retargeting between bipedal and quadrupedal skeletons because of the body part retargeting strategy and PAN. Our code is publicly available.

翻译：运动重定向是计算机图形学与计算机视觉领域的基础问题。现有方法通常具有诸多严格限制，例如源目标骨架需具有相同关节数量或共享相同拓扑结构。为解决该问题，我们注意到不同结构的骨架可能在关节数量存在差异的情况下仍具有某些共同身体部分。基于此观察，我们提出了一种新颖且灵活的运动重定向框架。该方法的核心思想是将身体部分作为基本重定向单元，而非直接对整个身体运动进行重定向。为增强运动编码器的空间建模能力，我们在运动编码阶段引入了姿态感知注意力网络（PAN）。该网络具有姿态感知特性，可基于输入姿态动态预测每个身体部分的关节权重，进而通过特征池化为各身体部分构建共享潜在空间。大量实验表明，与最先进方法相比，我们的方法在定性与定量层面均能生成更优的运动重定向结果。此外，得益于身体部分重定向策略与PAN，我们的框架甚至在更具挑战性的重定向场景（例如双足与四足骨架间的重定向）中仍能生成合理结果。相关代码已公开。