Research map / Video / Video generation
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
Shijun Shi, Jing Xu, Zhihang Li, Chunli Peng, Xiaoda Yang, Lijing Lu, Kai Hu, Jiangning Zhang
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 face region enhancement alone (ablation) | One-to-All-14B · TikTok | FVD: 355.2 -> 412.8 | Hurt |
| add reference-guided pose control on top of face region enhancement (ablation) | One-to-All-14B · TikTok | FVD: 412.8 -> 325.7 | Improved |
| add token replace for long video (ablation) | One-to-All-14B · TikTok | FVD: 325.7 -> 297.9 | Improved |
| add token replace for long video (ablation) | One-to-All-14B · TikTok | LPIPS: 0.275 -> 0.254 | Improved |
| add face region enhancement alone (ablation) | One-to-All · 100 misaligned pairs | CSIM: 0.6761 -> 0.7569 | Improved |
| add face region enhancement alone (ablation) | One-to-All · 100 misaligned pairs | APD-body: 0.0358 -> 0.0772 | Hurt |
| add reference-guided pose control on top of face enhancement (ablation) | One-to-All · 100 misaligned pairs | CSIM: 0.7569 -> 0.8172 | Improved |
| add reference-guided pose control on top of face enhancement (ablation) | One-to-All · 100 misaligned pairs | APD-body: 0.0772 -> 0.0367 | Improved |
| train reference first then reference+pose instead of pose first (ablation) | One-to-All-14B · TikTok | FVD: 408.7 -> 355.2 | Improved |
| train reference first instead of joint reference+pose training (ablation) | One-to-All-14B · TikTok | FVD: 415.3 -> 355.2 | Improved |
| apply RoPE with f=0 to cross-attention query (ablation) | HRFA · 81-frame inference | video quality | Improved |
| outpainting masking instead of random crop-and-resize (ablation) | One-to-All · qualitative | artifacts | Improved |
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.
- MimicMotion — MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance (ICML 2025) · better on 4 of 4 shared results
- Animate-X — Animate-X: Universal Character Image Animation with Enhanced Motion Representation (ICLR 2025) · better on 4 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
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024 · similarity 0.91)
- EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation (NeurIPS 2025 · similarity 0.90)
- Free-viewpoint Human Animation with Pose-correlated Reference Selection (CVPR 2025 · similarity 0.90)
- Animate-X: Universal Character Image Animation with Enhanced Motion Representation (ICLR 2025 · similarity 0.88)
- Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling (ICLR 2025 · similarity 0.87)
- ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters (AAAI 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.
