面向按身体部位灵活运动重定向的姿态感知注意力网络
Pose-aware Attention Network for Flexible Motion Retargeting by Body Part
AI总结：
针对现有运动重定向方法对骨骼结构限制严格的问题，提出以身体部位为基本单元的灵活重定向框架，引入姿态感知注意力网络增强空间建模能力，在多场景下实现了优于现有最优方法的重定向效果。
摘要：
运动重定向是计算机图形学和计算机视觉领域的一个基础问题。现有方法通常存在诸多严格限制，例如源-目标骨骼需要具有相同数量的关节或共享相同的拓扑结构。为解决这一问题，我们注意到，尽管关节数量存在差异，结构不同的骨骼仍可能拥有一些共同的身体部位。基于这一观察，我们提出了一种新颖的灵活运动重定向框架。我们方法的核心思想是将身体部位作为基本的重定向单元，而非直接对全身运动进行重定向。为提升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（Pose-aware Attention Network，PAN）。PAN具备姿态感知能力，因为它能够根据输入姿态动态预测每个身体部位内的关节权重，随后通过特征池化为每个身体部位构建共享的潜在空间。大量实验表明，我们的方法在定性和定量层面均能生成优于现有最优方法的运动重定向结果。此外，我们还证明，得益于身体部位重定向策略和PAN，即便在更具挑战性的重定向场景中——例如双足骨骼与四足骨骼之间的重定向——我们的框架也能生成合理的结果。我们的代码已公开。
英文摘要：
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.
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。
