Research map / Video / Video generation
ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis
KunHo Heo, SuYeon Kim, Yonghyun Gwon, Youngbin Kim, MyeongAh Cho
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 Part Guidance (part motions guide holistic generation) (ablation) | ParTY · HumanML3D | FID: 0.158 -> 0.086 | Improved |
| add Part-aware Text Grounding on top of PG (ablation) | ParTY · HumanML3D | FID: 0.086 -> 0.051 | Improved |
| add Holistic-Part Fusion on top of PG and PTG (ablation) | ParTY · HumanML3D | FID: 0.051 -> 0.035 | Improved |
| add Part Guidance, PTG and HPF (ablation) | ParTY · HumanML3D arms (part-level) | FID: 0.232 -> 0.133 | Improved |
| add Temporal-aware VQ-VAE (LTE+GTE) to MoMask at window 8 (ablation) | MoMask · HumanML3D (generation) | FID: 0.094 -> 0.039 | Improved |
| increase VQ-VAE window size without temporal enhancement (ablation) | MoMask · HumanML3D (generation) | FID: 0.045 -> 0.126 (window 4 -> 12) | Hurt |
| part-wise generation (ParCo) vs holistic | ParCo vs MoMask · HumanML3D | Temporal Coherence: 0.84 -> 0.49 | Hurt |
| ParTY vs MoMask on multimodality | ParTY · HumanML3D | MultiModality: 2.155 vs MDM 2.799; MoMask 1.241 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ParCo — ParCo: Part-Coordinating Text-to-Motion Synthesis (ECCV 2024) · better on 7 of 7 shared results
- BAMM — BAMM: Bidirectional Autoregressive Motion Model (ECCV 2024) · better on 5 of 5 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
- ParCo: Part-Coordinating Text-to-Motion Synthesis (ECCV 2024 · similarity 0.92)
- FrankenMotion: Part-level Human Motion Generation and Composition (CVPR 2026 · similarity 0.91)
- Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation (IJCV 2025 · similarity 0.91)
- HumanTOMATO: Text-aligned Whole-body Motion Generation (ICML 2024 · similarity 0.89)
- Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions (CVPR 2025 · similarity 0.89)
- Generating Human Motion in 3D Scenes from Text Descriptions (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.
