# TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation

arXiv: https://arxiv.org/abs/2606.12153 · HTML: https://mlsanity.com/paper/2606.12153/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [NeMF: Neural Motion Fields for Kinematic Animation](https://mlsanity.com/paper/2206.03287/) (2022)
- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [RigNet: Neural Rigging for Articulated Characters](https://mlsanity.com/paper/2005.00559/) (2020)
- [CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization](https://mlsanity.com/paper/2402.17214/) (2024)
- [SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations](https://mlsanity.com/paper/2505.02094/) (2025)
- [GANimator: Neural Motion Synthesis from a Single Sequence](https://mlsanity.com/paper/2205.02625/) (2022)
- [Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence](https://mlsanity.com/paper/2508.13139/) (2025)
- [LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model](https://mlsanity.com/paper/2405.03485/) (2024)
- [AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models](https://mlsanity.com/paper/2506.19851/) (2025)
- [A causal convolutional neural network for multi-subject motion modeling and generation](https://mlsanity.com/paper/2101.12276/) (2021)
- [Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior](https://mlsanity.com/paper/2310.20249/) (2023)
- [Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion](https://mlsanity.com/paper/2505.11013/) (2025)
- [PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation](https://mlsanity.com/paper/2508.08179/) (2025)

## Built on by (most cited first, 1 of 1)

- [CAST: Real-Time Motion Capture for Any Skeleton Topology](https://mlsanity.com/paper/2610.14856/) (2026)

## Abstract (arXiv)

The explosion of generative 3D assets has created a massive demand for animation, yet current motion capture methods remain brittle, restricted to species-specific templates (e.g., SMPL) or requiring labor-intensive manual rigging. We introduce TopoCap, the first unified framework capable of extracting motion from monocular video and retargeting it onto characters with arbitrary, unseen skeletal topologies, i.e., from bipeds to hexapods and inanimate objects, without test-time optimization. Our key insight is that while skeletal structures are combinatorial and discrete, the underlying physics of motion occupy a continuous, low-dimensional manifold. We materialize this insight via a two-stage generative pipeline. First, we learn a Universal Motion Manifold using a Graph CVAE that compresses heterogeneous kinematic chains into a shared, fixed-length latent code. By explicitly conditioning the decoder on a structural embedding of the target rig, we disentangle motion dynamics from skeletal topology. Second, we treat video-to-animation as a conditional flow matching problem, predicting these topology-agnostic codes from visual features. To learn this generalized prior, we introduce Mobjaverse, a massive-scale dataset curated from Objaverse-XL. Comprising over 5,000 unique skeletal topologies and 2 million frames, it exceeds the structural diversity of existing datasets by two orders of magnitude. Extensive experiments demonstrate that MethodMotion outperforms specialist models on human and quadruped benchmarks while enabling zero-shot retargeting for the long tail of 3D creatures. Dataset is publicly available at https://huggingface.co/datasets/duckduckplz/Mobjaverse.