AI Paper Atlas

Research map / Video / Video generation

Multi-identity Human Image Animation with Structural Video Diffusion

Zhenzhi Wang, Yixuan Li, Yanhong Zeng, Yuwei Guo, Dahua Lin, Tianfan Xue, Bo Dai

ICCV 2025 · Video › Video generation · approach: Diffusion-based human image animation · 12 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 ID-embedding (ablation)CamAnimate baseline · Multi-ID test setFID: 54.09 -> 33.75Improved
add ID-embedding (ablation)CamAnimate baseline · Multi-ID test setPSNR: 19.552 -> 20.374Improved
add ID-embedding (ablation)CamAnimate baseline · Multi-ID test setFVD: 982.1 -> 873.5Improved
add depth/multi-modality prediction (ablation)CamAnimate baseline · Multi-ID test setFID: 54.09 -> 47.67Improved
add depth/multi-modality prediction (ablation)CamAnimate baseline · Multi-ID test setSSIM: 0.649 -> 0.668Improved
add depth prediction on top of ID-embedding (ablation)ID-embedding model · Multi-ID test setFID: 33.75 -> 30.57Improved
add depth prediction on top of ID-embedding (ablation)ID-embedding model · Multi-ID test setFVD: 873.5 -> 878.2Hurt
add normal prediction on top of ID-embedding (ablation)ID-embedding model · Multi-ID test setFID: 33.75 -> 60.58Hurt
add normal prediction on top of ID-embedding (ablation)ID-embedding model · Multi-ID test setPSNR: 20.374 -> 19.037Hurt
add normal prediction alongside depth (ablation)ID-embedding + depth model · Multi-ID test setFID: 30.57 -> 56.78Hurt
full method vs CamAnimateStructural Video Diffusion · Multi-ID test setFID: 54.09 -> 30.57Improved
full method vs CamAnimateStructural Video Diffusion · Multi-ID test setFVD: 982.1 -> 878.2Improved

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