AnyTop: Character Animation Diffusion with Any Topology

TL;DR

AnyTop is a novel diffusion model that generates diverse character motions from skeletal structures, effectively handling arbitrary topologies and enabling semantic understanding and downstream applications.

Contribution

We introduce AnyTop, a transformer-based diffusion model that learns to generate motions for arbitrary skeletons using topology and semantic joint descriptions.

Findings

Generalizes well with minimal training data

Produces motions for unseen skeletons

Latent space supports downstream tasks

Abstract

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.