Research map / Video / Video generation
FrankenMotion: Part-level Human Motion Generation and Composition
Chuqiao Li, Xianghui Xie, Yong Cao, Andreas Geiger, Gerard Pons-Moll
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 action-level text to part-level text (ablation) | FrankenMotion · FrankenStein test (Avg-part) | R@3: 56.34 -> 57.74 | Improved |
| add sequence-level text on top of part+action text (ablation) | FrankenMotion · FrankenStein test (Avg-part) | R@3: 57.74 -> 58.97 | Improved |
| add action and sequence text (ablation) | FrankenMotion · FrankenStein test (realism) | FID: 0.08 -> 0.05 | Improved |
| add sequence text on top of part+action text (ablation) | FrankenMotion · FrankenStein test (Per-action) | R@3: 65.39 -> 65.79 | No clear effect |
| part-level text only conditioning (ablation) | FrankenMotion · FrankenStein test (Avg-part) | M2T: 0.69 -> 0.69 | No clear effect |
| hierarchical part conditioning vs STMC post-hoc composition | FrankenMotion · FrankenStein test (Per-seq) | R@1: 43.58 -> 65.27 | Improved |
| hierarchical part conditioning vs UniMotion | FrankenMotion · FrankenStein test (Avg-part) | R@1: 45.72 -> 47.21 | Improved |
| FrankenMotion vs UniMotion on realism | FrankenMotion · FrankenStein test (Per-action) | FID: 0.05 -> 0.04 | Improved |
| FrankenMotion vs DartControl per-seq | FrankenMotion · FrankenStein test (Per-seq) | R@1: 54.28 -> 65.27 | Improved |
Closest papers by meaning
- Human Motion Diffusion as a Generative Prior (ICLR 2024 · similarity 0.90)
- SnapMoGen: Human Motion Generation from Expressive Texts (NeurIPS 2025 · similarity 0.90)
- HumanTOMATO: Text-aligned Whole-body Motion Generation (ICML 2024 · similarity 0.89)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.89)
- Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions (CVPR 2025 · similarity 0.89)
- MMM: Generative Masked Motion Model (CVPR 2024 · 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.
