Research map / Video / Video generation
EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
Yufei Cai, Hu Han, Yuxiang Wei, Shiguang Shan, Xilin Chen
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 the scaler module (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | motion fidelity: 0.8135 -> 0.8470 | Improved |
| add the scaler module (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | temporal consistency: 0.9244 -> 0.9291 | Improved |
| add the scaler module (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | text alignment: 0.2638 -> 0.2712 | Improved |
| add data filtering to constructed training data (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | motion fidelity: 0.8278 -> 0.8470 | Improved |
| add data filtering to constructed training data (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | temporal consistency: 0.9237 -> 0.9291 | Improved |
| inject into all upsampling blocks instead of only upblock 1 (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | motion fidelity: 0.6374 -> 0.8470 | Improved |
| inject into all upsampling blocks instead of only upblock 1 (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | text alignment: 0.2789 -> 0.2712 | Hurt |
| inject into all upsampling blocks instead of upblocks 1 and 2 (ablation) | EfficientMT · Motion transfer ablation (AnimateDiff) | motion fidelity: 0.7236 -> 0.8470 | Improved |
| use EfficientMT instead of optimization-based MotionClone | AnimateDiff · Motion transfer test set | time cost: 190s -> 16s | Improved |
| use EfficientMT instead of MotionDirector | AnimateDiff · Motion transfer test set | time cost: 473s -> 16s | Improved |
| use EfficientMT instead of MotionClone | AnimateDiff · Motion transfer test set | motion fidelity: 0.8569 -> 0.8470 | Hurt |
| use EfficientMT instead of MotionInversion | VideoCrafter2 · Motion transfer test set | motion fidelity: 0.7373 -> 0.7116 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MotionClone — MotionClone: Training-Free Motion Cloning for Controllable Video Generation (ICLR 2025) · better on 3 of 4 shared results
- ControlVideo — ControlVideo: Training-free Controllable Text-to-video Generation (ICLR 2024) · better on 2 of 2 shared results
- VideoComposer — VideoComposer: Compositional Video Synthesis with Motion Controllability (NeurIPS 2023) · better on 2 of 2 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
- Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning (NeurIPS 2024 · similarity 0.90)
- Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis (CVPR 2025 · similarity 0.89)
- Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer (CVPR 2024 · similarity 0.89)
- Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think (CVPR 2025 · similarity 0.89)
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (CVPR 2025 · similarity 0.88)
- ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way (CVPR 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.
