AI Paper Atlas

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

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
add face region enhancement alone (ablation)One-to-All-14B · TikTokFVD: 355.2 -> 412.8Hurt
add reference-guided pose control on top of face region enhancement (ablation)One-to-All-14B · TikTokFVD: 412.8 -> 325.7Improved
add token replace for long video (ablation)One-to-All-14B · TikTokFVD: 325.7 -> 297.9Improved
add token replace for long video (ablation)One-to-All-14B · TikTokLPIPS: 0.275 -> 0.254Improved
add face region enhancement alone (ablation)One-to-All · 100 misaligned pairsCSIM: 0.6761 -> 0.7569Improved
add face region enhancement alone (ablation)One-to-All · 100 misaligned pairsAPD-body: 0.0358 -> 0.0772Hurt
add reference-guided pose control on top of face enhancement (ablation)One-to-All · 100 misaligned pairsCSIM: 0.7569 -> 0.8172Improved
add reference-guided pose control on top of face enhancement (ablation)One-to-All · 100 misaligned pairsAPD-body: 0.0772 -> 0.0367Improved
train reference first then reference+pose instead of pose first (ablation)One-to-All-14B · TikTokFVD: 408.7 -> 355.2Improved
train reference first instead of joint reference+pose training (ablation)One-to-All-14B · TikTokFVD: 415.3 -> 355.2Improved
apply RoPE with f=0 to cross-attention query (ablation)HRFA · 81-frame inferencevideo qualityImproved
outpainting masking instead of random crop-and-resize (ablation)One-to-All · qualitativeartifactsImproved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy