Research map / Video / Video generation
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video
Xinyao Zhang, Wenkai Dong, YuXin Song, Bo Fang, Qi Zhang, Jing Wang, Fan Chen, Hui Zhang, Haocheng Feng, Yu Lu, Hang Zhou, Chun Yuan and 1 more
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 Semantic Anchoring (ablation) | SAMA (Wan2.2-T2V-5B baseline) · VIE-Bench | Overall: 6.312 -> 6.696 | Improved |
| add Motion Alignment (ablation) | SAMA (Wan2.2-T2V-5B baseline) · VIE-Bench | Overall: 6.312 -> 6.711 | Improved |
| add both SA and MA (ablation) | SAMA (Wan2.2-T2V-5B baseline) · VIE-Bench | Overall: 6.312 -> 7.095 | Improved |
| add Semantic Anchoring (ablation) | SAMA (Wan2.2-T2V-5B baseline) · training loss | diffusion loss convergence | Improved |
| use learned type embeddings instead of shifted RoPE (ablation) | SAMA (Wan2.2-T2V-5B baseline) · VIE-Bench replace | Overall: 6.498 -> 6.975 | Improved |
| pretrain only (no paired video editing data) | SAMA · VIE-Bench zero-shot | qualitative | Mixed |
| use SAMA instead of best open-source baseline | SAMA · OpenVE-Bench Local Add | score: 2.54 vs UniVideo 2.98 | Mixed |
| SAMA vs ReCo on Style | SAMA · ReCo-Bench Style | S_EA: 9.24 vs ReCo 9.42 | Mixed |
Later papers that compared with this method
1 later accepted paper reports SAMA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Transforming Image Editors into Video Editors (NeurIPS 2026 · better on 1 of 1 shared result)
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
- Transforming Image Editors into Video Editors (NeurIPS 2026 · similarity 0.89)
- Dynamic Motion Blending for Versatile Motion Editing (CVPR 2025 · similarity 0.88)
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (NeurIPS 2026 · similarity 0.88)
- Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists (NeurIPS 2025 · similarity 0.88)
- Text-Vision Co-Instructed Image Editing (NeurIPS 2026 · similarity 0.87)
- VicEdit: Learning to Edit Videos from Visual In-Context Examples (NeurIPS 2026 · 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.
