Research map / Video / Video generation
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei, Jing Shi, Ming-Hsuan Yang, Zhixin Shu
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 prompt reasoning (ablation) | Motion-controlled generator · MotiBench | Semantic: 0.337 -> 0.544 | Improved |
| add motion reasoning on top of prompt reasoning (ablation) | Motion-controlled generator · MotiBench | Physical: 0.237 -> 0.285 | Improved |
| add confidence-aware control (ablation) | MotiMotion · MotiBench | Physical: 0.285 -> 0.302 | Improved |
| add confidence-aware control (ablation) | MotiMotion · MotiBench | Photo: 0.493 -> 0.520 | Improved |
| add prompt reasoning without user prompt (ablation) | Image + Trajectories · MotiBench | Semantic: 0.272 -> 0.473 | Improved |
| add reasoning to MagicMotion | MagicMotion · MotiBench | Physical: 0.157 -> 0.199 | Improved |
| add reasoning to MagicMotion | MagicMotion · MotiBench | Photo: 0.550 -> 0.528 | Hurt |
| add reasoning to Wan-Move | Wan-Move · MotiBench | Semantic: 0.511 -> 0.588 | Improved |
| use two-stage instead of one-stage reasoning (ablation) | MotiMotion · MotiBench | Physical: 0.302 -> 0.319 | No clear effect |
| add confidence-aware control to reduce inaccurate trajectories (ablation) | MotiMotion · MotiBench failure analysis | Inaccurate rate (%): 4.8 -> 3.2 | Improved |
| replace MagicMotion with MotiMotion | video generator · MotiBench human 2AFC | win rate (%): 97.9 | 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.
- Wan-Move — Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 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
- DIVER: Disentangling Camera–Object and Active–Passive Motion for Video Generation (ECCV 2026 · similarity 0.89)
- MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance (ICCV 2025 · similarity 0.88)
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.88)
- Motion Prompting: Controlling Video Generation with Motion Trajectories (CVPR 2025 · similarity 0.88)
- MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction (NeurIPS 2026 · similarity 0.87)
- TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation (CVPR 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.
