可学习展平实现到多样骨骼的运动重定向
Retargeting Motions to Diverse Skeletons via Learnable Flattening
浏览论文内容
中文总结 AI 辅助
本文提出一种Transformer自编码器，通过可学习展平骨骼图实现跨拓扑运动重定向，在零样本下将全局关节误差降低43-47%，并获用户研究最高评价。
中文摘要 AI 辅助
跨结构运动重定向旨在不同骨骼拓扑之间转移运动。尽管近期有所进展，现有最先进模型在零样本设置（即训练时未见的不同拓扑骨骼）下仍难以保证可靠性，且近期基于Transformer的尝试未能超越专门的几何方法。我们通过一种Transformer自编码器弥合了这一差距，该自编码器学习一个拓扑不变且平移不变的潜在空间。我们的核心贡献是对骨骼图的可学习展平，它同时捕获局部依赖和全局结构。与标准Transformer架构（将位置信息添加到令牌内容中）不同，我们将基于图的位置编码以乘法方式集成，这一设计选择直接源于我们的展平公式。所得模型在单一统一架构内处理多样骨骼拓扑，并以完全无监督方式训练，无需成对重定向数据。消融研究表明，图编码、乘法公式和Transformer主干对性能至关重要。在零样本评估中，我们的方法将全局关节位置误差比当前基准降低了43-47%。一项包含专家动画师的用户研究（n=37）进一步将我们的方法在运动对齐和物理合理性方面评为最高（p<0.05）。这些结果表明，我们的模型设计是使Transformer架构对运动重定向有效的关键，超越了现有方法。
英文摘要
Cross-structural motion retargeting aims to transfer motion between different skeletal topologies. Despite recent progress, existing state-of-the-art models struggle with reliability in zero-shot settings, i.e. skeletons with different topologies which were unseen during training, and recent Transformer-based attempts have failed to outperform specialized geometric methods. We bridge this gap with a Transformer Autoencoder that learns a topology- and translation-invariant latent space. Our core contribution is a learnable flattening of skeletal graphs that captures both local dependencies and global structure. Unlike the standard transformer architecture, which adds positional information to token content, we integrate graph-based positional encodings multiplicatively, a design choice that follows directly from our flattening formulation. The resulting model handles diverse skeletal topologies within a single unified architecture and trains in a fully unsupervised manner, requiring no paired retargeting data. Ablation studies show, that the graph encodings, multiplicative formulation, and Transformer backbone is critical for the performance. In zero-shot evaluations, our method reduces global joint position error by $43-47\%$ over current benchmarks. A user study ($n = 37$), including expert animators, further ranks our approach highest in motion alignment and physical plausibility ($p < 0.05$). These results demonstrate that our model design is key to making transformer architectures effective for motion retargeting, outperforming existing approaches.
发表机构
- Institute of Computer Science, University of Göttingen（哥廷根大学计算机科学研究所）
- Campus Institute Data Science, University Göttingen（哥廷根大学数据科学校园研究所）
- Pantomim P.S.A
机构由 AI 辅助整理，请以论文原文为准。
