Research map / Video / Video generation
MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes
Ye Tao, Yuxin Yao, Kendong Liu, Dapeng Wu, Junhui Hou
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 DINO-based texture-semantic injection via skinning-weighted cross attention (ablation) | SkelMo · SkelMo test set | MPJPE: 0.234 -> 0.054 | Improved |
| add bidirectional video-skeleton cross attention fusion (ablation) | SkelMo · SkelMo test set | MPJPE: 0.118 -> 0.054 | Improved |
| use global xyz coordinates instead of relative representation (ablation) | SkelMo · SkelMo test set | MPJPE: 0.285 -> 0.054 | Improved |
| use global xyz coordinates instead of relative representation (ablation) | SkelMo · SkelMo test set | Chamfer Distance: 0.340 -> 0.086 | Improved |
| add texture-semantic injection (ablation) | SkelMo · SkelMo test set | Chamfer Distance: 0.235 -> 0.086 | Improved |
| use SkelMo instead of Puppeteer | skeletal motion generation · SkelMo test set | MPJPE: 0.161 -> 0.054 | Improved |
| use SkelMo instead of vertex-trajectory methods (Motion 3-to-4, ActionMesh) | video-to-4D motion · SkelMo test set | Chamfer Distance: 0.418 -> 0.086 | Improved |
| use auto-rigged skeletons instead of ground-truth rigs | SkelMo · vertex-space metrics | Vertex-CD: 0.107 -> 0.146 | Hurt |
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.
- ActionMesh — ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion (CVPR 2026) · 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
- How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects (ICML 2025 · similarity 0.90)
- SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons (CVPR 2025 · similarity 0.89)
- TapMo: Shape-aware Motion Generation of Skeleton-free Characters (ICLR 2024 · similarity 0.89)
- Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (NeurIPS 2026 · similarity 0.88)
- Puppeteer: Rig and Animate Your 3D Models (NeurIPS 2025 · similarity 0.88)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.88)
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.
