AnyTop: Character Animation Diffusion with Any Topology
This work addresses a longstanding problem in computer graphics for animators and game developers by enabling motion generation for any skeleton topology, though it appears incremental as it builds on existing diffusion and transformer methods.
The paper tackles the challenge of generating motion for arbitrary skeletons in character animation by introducing AnyTop, a diffusion model that uses skeletal structure as input to produce motions for diverse characters, demonstrating generalization with as few as three training examples per topology and enabling downstream tasks like motion editing.
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.