AI Paper Atlas

Research map / Video / Video generation

MultiAnimate: Pose-Guided Image Animation Made Extensible

Yingcheng Hu, Haowen Gong, Chuanguang Yang, Zhulin An, Yongjun Xu, Songhua Liu

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 3 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
use mask-driven Identifier Assigner and Adapter over UniAnimate-DiTMultiAnimate · Swing DancePSNR: 16.15 -> 19.40Improved
use mask-driven Identifier Assigner and Adapter over UniAnimate-DiTMultiAnimate · Swing DanceFVD: 891.89 -> 648.84Improved
use Extended model (up to 7 characters) over UniAnimate-DiTMultiAnimate · Unseen dance videosFVD: 624.45 -> 358.74Improved
use Extended model over UniAnimate-DiTMultiAnimate · Unseen dance videosPSNR: 17.94 -> 23.24Improved
use Stage 1 model over UniAnimate-DiT without training on Gen-datasetMultiAnimate · Gen-datasetFID-VID: 32.10 -> 33.57Hurt
use Stage 1 model over VACEMultiAnimate · Gen-datasetLPIPS: 0.231 -> 0.251Hurt
add Gen-dataset training (Stage 2 model) (ablation)MultiAnimate · Gen-dataset samplessubject and background consistency (qualitative)Improved
use mask-driven design instead of addition-driven per-person feature summation (ablation)MultiAnimate · more characters than traininggeneralization to more characters (qualitative)Improved
add Identifier Assigner and Adapter (mask-driven design) (ablation)MultiAnimate · Swing Dance / unseen videosidentity consistency (qualitative)Improved
compare to single-character baselinesMultiAnimate · TikTok (single character)PSNR: 17.76 -> 23.68Improved
compare to single-character baselinesMultiAnimate · TikTok (single character)FVD: 615.27 -> 342.48Improved
randomly assign identifiers from a label bank during training (ablation)MultiAnimate · Swing Dancesymmetry problem (qualitative)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.

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