Research map / Video / Video generation
FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
Mingyuan Zhang, Huirong Li, Zhongang Cai, Jiawei Ren, Lei Yang, Ziwei Liu
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 temporal dependence to the attention (ablation) | FineMoGen baseline · HuMMan-MoGen temporal composition (zero-shot) | FID: 3.79 -> 2.48 | Improved |
| add sparsely-activated MoE (ablation) | FineMoGen baseline · HuMMan-MoGen temporal composition (zero-shot) | FID: 3.79 -> 3.09 | Improved |
| add spatial dependence alone (ablation) | FineMoGen baseline · HuMMan-MoGen temporal composition (zero-shot) | FID: 3.79 -> 4.51 | Hurt |
| combine spatial, temporal and MoE (ablation) | FineMoGen baseline · HuMMan-MoGen temporal composition (zero-shot) | FID: 3.79 -> 1.34 | Improved |
| add spatial independence alone (ablation) | FineMoGen baseline · HuMMan-MoGen spatial composition (zero-shot) | FID: 2.87 -> 2.04 | Improved |
| add temporal independence alone (ablation) | FineMoGen baseline · HuMMan-MoGen spatial composition (zero-shot) | FID: 2.87 -> 3.56 | Hurt |
| add MoE alone (ablation) | FineMoGen baseline · HuMMan-MoGen spatial composition (zero-shot) | FID: 2.87 -> 2.41 | Improved |
| train fully-supervised on temporal composition data instead of zero-shot | FineMoGen · BABEL | FID: 0.84 -> 0.73 | Improved |
| FineMoGen versus ReMoDiffuse on standard text-to-motion | FineMoGen · HumanML3D | FID: 0.103 -> 0.151 | Hurt |
Later papers that compared with this method
6 later accepted papers report FineMoGen as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- CoMA: Compositional Human Motion Generation with Multi-modal Agents (AAAI 2026 · better on 1 of 1 shared result)
- Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation (IJCV 2025 · better on 4 of 4 shared results)
- FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing (ICCV 2025 · better on 2 of 2 shared results)
- MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls (AAAI 2025 · better on 1 of 1 shared result)
- CoMo: Controllable Motion Generation through Language Guided Pose Code Editing (ECCV 2024 · better on 0 of 3 shared results)
- Large Motion Model for Unified Multi-Modal Motion Generation (ECCV 2024 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- ReMoDiffuse — ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model (ICCV 2023) · better on 1 of 4 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
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.89)
- Motion Prompting: Controlling Video Generation with Motion Trajectories (CVPR 2025 · similarity 0.88)
- SnapMoGen: Human Motion Generation from Expressive Texts (NeurIPS 2025 · similarity 0.88)
- Trajectory attention for fine-grained video motion control (ICLR 2025 · similarity 0.88)
- OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers (CVPR 2024 · similarity 0.88)
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · 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.
