# GaussiAnimate: Rig Animatable Categories with Level of Dynamics

arXiv: https://arxiv.org/abs/2604.08547 · HTML: https://mlsanity.com/paper/2604.08547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 87 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 30 of 40)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes](https://mlsanity.com/paper/2312.14937/) (2023)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [TAVA: Template-free Animatable Volumetric Actors](https://mlsanity.com/paper/2206.08929/) (2022)
- [HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion](https://mlsanity.com/paper/2305.06356/) (2023)
- [4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface](https://mlsanity.com/paper/2105.01905/) (2021)
- [Easi3R: Estimating Disentangled Motion from DUSt3R Without Training](https://mlsanity.com/paper/2503.24391/) (2025)
- [HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics](https://mlsanity.com/paper/2212.07242/) (2022)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations](https://mlsanity.com/paper/2404.04421/) (2024)
- [RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets](https://mlsanity.com/paper/2502.09615/) (2025)
- [One Model to Rig Them All: Diverse Skeleton Rigging with UniRig](https://mlsanity.com/paper/2504.12451/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation](https://mlsanity.com/paper/2311.12194/) (2023)
- [Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks](https://mlsanity.com/paper/2205.01355/) (2022)
- [Point2Skeleton: Learning Skeletal Representations from Point Clouds](https://mlsanity.com/paper/2012.00230/) (2020)
- [RigNet: Neural Rigging for Articulated Characters](https://mlsanity.com/paper/2005.00559/) (2020)
- [Feat2GS: Probing Visual Foundation Models with Gaussian Splatting](https://mlsanity.com/paper/2412.09606/) (2024)
- [Anymate: A Dataset and Baselines for Learning 3D Object Rigging](https://mlsanity.com/paper/2505.06227/) (2025)
- [Coverage Axis: Inner Point Selection for 3D Shape Skeletonization](https://mlsanity.com/paper/2110.00965/) (2021)
- [Morig: Motion-aware rigging of character meshes from point clouds](https://mlsanity.com/paper/2210.09463/) (2022)
- [Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence](https://mlsanity.com/paper/2508.13139/) (2025)
- [ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion](https://mlsanity.com/paper/2601.16148/) (2026)
- [Template-free Articulated Neural Point Clouds for Reposable View Synthesis](https://mlsanity.com/paper/2305.19065/) (2023)
- [Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis](https://mlsanity.com/paper/2601.14253/) (2026)

## Abstract (arXiv)

We propose Skelebones, a Scaffold-Skin Rigging System built on three steps: (1) Bones compress temporally consistent Gaussian or mesh sequences into free-form bones with smooth skinning weights, approximating non-rigid deformations via linear blend skinning (LBS); (2) Skeleton extracts the Mean Curvature Skeleton (MCS) from the canonical shape and temporally refines its topology and kinematics into a compact skeletal structure; and (3) Binding connects the skeleton and bones through non-parametric Partwise Motion Matching (PartMM), which synthesizes novel bone motions by matching, retrieving, and blending existing ones. Together, these steps compress the dynamics of 4D shapes into compact skelebones that are simultaneously controllable and expressive. The resulting representation is category-agnostic, meaning template-free; motion-adaptive, with dynamic topology; and topology-correct, with a skeleton consistent with the surface geometry. PartMM requires no learning. We validate our method on both synthetic and real-world datasets, achieving substantial reanimation improvements on unseen poses: a 17.3 dB PSNR gain over LBS on DNA-Rendering and a 45.6 dB gain over Bag-of-Bones on ActorsHQ, while preserving high rendering fidelity for characters with complex non-rigid dynamics. PartMM generalizes robustly to both Gaussian and mesh representations, excelling in low-data regimes of approximately 1,000 frames, with a 48.4 RMSE improvement over LBS and improvements of more than 20 over GRU- and MLP-based methods. Code will be publicly released at https://cookmaker.cn/gaussianimate/.