用骨骼结构生成任意角色动作，仅需少量样本即可泛化。
AnyTop: Character Animation Diffusion with Any Topology
- 基于变换器的去噪网络，融合拓扑信息建模任意骨骼。
- 每种骨架仅需3个训练样本，即可生成未见角色的动作。
- 适合角色动画生成、动作编辑与关节对应等下游任务。
在计算机图形学中，为任意骨骼生成动作是一个长期存在的挑战，主要因数据集多样性不足和数据不规则性而难以研究。本文提出AnyTop，一种仅以骨骼结构为输入的扩散模型，可为具有不同运动特性的多样化角色生成动作。该模型采用针对任意骨骼设计的基于变压器的去噪网络，并将拓扑信息融入传统注意力机制。通过在潜在特征表示中引入文本化关节描述，AnyTop学习跨不同骨骼的语义对应关系。评估表明，即使每种拓扑结构仅有三个训练样本，AnyTop仍具备良好泛化能力，可生成未见过骨骼的动作。此外，模型的潜在空间极具信息量，支持关节对应、时间分割和动作编辑等下游任务。项目主页（https://anytop2025.github.io/Anytop-page）提供视频与代码链接。
原文摘要 · Abstract (English)
Generating motion for arbitrary skeletons is a longstanding challenge in computer graphics, remaining largely unexplored due to the scarcity of diverse datasets and the irregular nature of the data. In this work, we introduce AnyTop, a diffusion model that generates motions for diverse characters with distinct motion dynamics, using only their skeletal structure as input. Our work features a transformer-based denoising network, tailored for arbitrary skeleton learning, integrating topology information into the traditional attention mechanism. Additionally, by incorporating textual joint descriptions into the latent feature representation, AnyTop learns semantic correspondences between joints across diverse skeletons. Our evaluation demonstrates that AnyTop generalizes well, even with as few as three training examples per topology, and can produce motions for unseen skeletons as well. Furthermore, our model's latent space is highly informative, enabling downstream tasks such as joint correspondence, temporal segmentation and motion editing. Our webpage, https://anytop2025.github.io/Anytop-page, includes links to videos and code.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。