# AnyTop: Character Animation Diffusion with Any Topology

arXiv: https://arxiv.org/abs/2502.17327 · HTML: https://mlsanity.com/paper/2502.17327/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 63 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 30 of 36)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Rethinking Graph Transformers with Spectral Attention](https://mlsanity.com/paper/2106.03893/) (2021)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [Guided Motion Diffusion for Controllable Human Motion Synthesis](https://mlsanity.com/paper/2305.12577/) (2023)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence](https://mlsanity.com/paper/2311.17034/) (2023)
- [GRPE: Relative Positional Encoding for Graph Transformer](https://mlsanity.com/paper/2201.12787/) (2022)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [Deep Learning on Lie Groups for Skeleton-based Action Recognition](https://mlsanity.com/paper/1612.05877/) (2016)
- [MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion](https://mlsanity.com/paper/2310.14729/) (2023)
- [Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry](https://mlsanity.com/paper/2303.08658/) (2023)
- [Contact-Aware Retargeting of Skinned Motion](https://mlsanity.com/paper/2109.07431/) (2021)
- [AMD: Autoregressive Motion Diffusion](https://mlsanity.com/paper/2305.09381/) (2023)
- [GANimator: Neural Motion Synthesis from a Single Sequence](https://mlsanity.com/paper/2205.02625/) (2022)
- [Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction](https://mlsanity.com/paper/2211.10278/) (2022)
- [HUMOS: Human Motion Model Conditioned on Body Shape](https://mlsanity.com/paper/2409.03944/) (2024)

## Built on by (most cited first, 30 of 41)

- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence](https://mlsanity.com/paper/2508.13139/) (2025)
- [AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models](https://mlsanity.com/paper/2506.19851/) (2025)
- [MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos](https://mlsanity.com/paper/2512.10881/) (2025)
- [Motion Generation: A Survey of Generative Approaches and Benchmarks](https://mlsanity.com/paper/2507.05419/) (2025)
- [Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization](https://mlsanity.com/paper/2506.11430/) (2025)
- [ARMO: Autoregressive Rigging for Multi-Category Objects](https://mlsanity.com/paper/2503.20663/) (2025)
- [X-MoGen: Unified Motion Generation across Humans and Animals](https://mlsanity.com/paper/2508.05162/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation](https://mlsanity.com/paper/2602.18873/) (2026)
- [Multi-Embodiment Robotic Retargeting via Guided Diffusion Model](https://mlsanity.com/paper/2505.20857/) (2025)
- [PALUM: Part-based Attention Learning for Unified Motion Retargeting](https://mlsanity.com/paper/2601.07272/) (2026)
- [SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking](https://mlsanity.com/paper/2602.04441/) (2026)
- [NECromancer: Breathing Life into Skeletons via BVH Animation](https://mlsanity.com/paper/2602.06548/) (2026)
- [AniGen: Unified S3 Fields for Animatable 3D Asset Generation](https://mlsanity.com/paper/2604.08746/) (2026)
- [ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes](https://mlsanity.com/paper/2604.17623/) (2026)
- [Topology-Agnostic Animal Motion Generation from Text Prompt](https://mlsanity.com/paper/2512.10352/) (2025)
- [MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons](https://mlsanity.com/paper/2604.28130/) (2026)
- [ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting](https://mlsanity.com/paper/2605.06593/) (2026)
- [MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer](https://mlsanity.com/paper/2511.18370/) (2025)
- [DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies](https://mlsanity.com/paper/2603.17704/) (2026)
- [A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting](https://mlsanity.com/paper/2604.13427/) (2026)
- [TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation](https://mlsanity.com/paper/2606.12153/) (2026)
- [Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories](https://mlsanity.com/paper/2606.25344/) (2026)
- [SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology](https://mlsanity.com/paper/2607.02148/) (2026)
- [UniMate: One Unified Model to Animate Diverse Skeletons](https://mlsanity.com/paper/2609.05415/) (2026)
- [FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds](https://mlsanity.com/paper/2512.09423/) (2025)
- [Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation](https://mlsanity.com/paper/2605.13129/) (2026)
- [R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow](https://mlsanity.com/paper/2605.13838/) (2026)
- [Mat'ern Noise for Triangulation-Agnostic Flow Matching on Meshes](https://mlsanity.com/paper/2605.19305/) (2026)

## Abstract (arXiv)

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.