AI Paper Atlas

Research map / Video / Video generation

MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers

Yuechen Zhang, Yaoyang Liu, Bin Xia, Bohao Peng, Zexin Yan, Eric Lo, Jiaya Jia

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 27 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 Conditioned Adaptive Normalization (ablation)MagicMirror · ablation (half training)ID similarity: 0.886 -> 0.911Improved
add Conditioned Adaptive Normalization (ablation)MagicMirror · ablation (half training)FM_inter: 0.568 -> 0.665Improved
add image pre-training (ablation)MagicMirror · ablation (half training)ID similarity: 0.883 -> 0.911Improved
add image pre-training (ablation)MagicMirror · ablation (half training)FM_inter: 0.559 -> 0.665Improved
use dual-branch (identity + structural) face embedding instead of identity branch only (ablation)MagicMirror · ablation (half training)FM_inter: 0.572 -> 0.654Improved
use dual-branch instead of structural branch only (ablation)MagicMirror · ablation (half training)FM_inter: 0.584 -> 0.654Improved
use dual-branch instead of single branch (ablation)MagicMirror · ablation (half training)ID similarity: 0.865 -> 0.870Improved
add masks and CAN pipeline on top of dual branch to reach full model (ablation)MagicMirror · ablation (half training)ID similarity: 0.870 -> 0.911Improved
evaluate ID-Animator at 512x512 instead of 480x720ID-Animator · ID-preserved video generationID similarity: 0.923 -> 0.921No clear effect
MagicMirror vs CogVideoX-I2VCogVideoX-I2V · video generationDynamic Degree: 0.660 -> 0.705Improved
MagicMirror vs ConsisIDConsisID · video generationFM_ref: 0.652 -> 0.730Improved
MagicMirror vs ID-Animator on ID similarityID-Animator · video generationAverage ID Similarity: 0.923 -> 0.922No clear effect

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