Research map / Video / Video generation
RigMo: Unifying Rig and Motion Learning for Generative Animation
Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add geodesic-aware weight refinement (ablation) | RigMo · DeformingThings4D val | CD-L1 (x1e-2): 2.37 -> 1.73 | Improved |
| add geodesic-aware weight refinement (ablation) | RigMo · DeformingThings4D val | CD-L2 (x1e-2): 2.07 -> 1.26 | Improved |
| increase bone tokens from 48 to 128 (ablation) | RigMo · DeformingThings4D val | CD-L1 (x1e-2): 1.91 -> 1.73 | Improved |
| increase bone tokens from 48 to 128 (ablation) | RigMo · DeformingThings4D val | CD-L2 (x1e-2): 1.48 -> 1.26 | Improved |
| add frame-mask guidance to MotionDiT (ablation) | MotionDiT · 1->1 val | CD-L1 (x1e-2): 2.48 -> 1.77 | Improved |
| add frame-mask guidance to MotionDiT (ablation) | MotionDiT · 1->9 val | CD-L1 (x1e-2): 3.10 -> 1.86 | Improved |
| add decoded skinning weights and bone centers to latent rig conditioning (ablation) | MotionDiT · 1->1 val | CD-L1 (x1e-2): 2.01 -> 1.77 | Improved |
| add decoded skinning weights and bone centers to latent rig conditioning (ablation) | MotionDiT · 1->9 val | CD-L1 (x1e-2): 2.51 -> 1.86 | Improved |
| add decoded skinning weights and bone centers to latent rig conditioning (ablation) | MotionDiT · 1->9 val | CD-L2 (x1e-2): 1.78 -> 1.37 | Improved |
| replace per-case optimization with feed-forward RigMo on cross-motion transfer | Per-Case Optimization · DT4D cross-motion transfer | CD-L1 (x1e-3): 68.8 -> 13.82 | Improved |
| replace UniRig + optimization with RigMo | UniRig + Optimization · DT4D mean | CD-L1 (x1e-3): 42.95 -> 12.46 | Improved |
| replace AnimateAnyMesh with RigMo on inference time | AnimateAnyMesh · DT4D reconstruction | time (20 frames): 2.8s -> 0.74s | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AnimateAnyMesh — AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation (ICCV 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (NeurIPS 2026 · similarity 0.91)
- Puppeteer: Rig and Animate Your 3D Models (NeurIPS 2025 · similarity 0.88)
- TapMo: Shape-aware Motion Generation of Skeleton-free Characters (ICLR 2024 · similarity 0.88)
- Articulated Kinematics Distillation from Video Diffusion Models (CVPR 2025 · similarity 0.87)
- RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos (CVPR 2025 · similarity 0.87)
- How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects (ICML 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
