AI Paper Atlas

Research map / Video / Video generation

InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions

Zhenzhi Wang, Jiaqi Yang, Jianwen Jiang, Chao Liang, Gaojie Lin, Zerong Zheng, Ceyuan Yang, Yuan Zhang, Mingyuan Gao, Dahua Lin

ICLR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 20 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 predicted-mask local audio injection instead of global audio (ablation)InterActHuman · Multi-Person Test Set (full-body)Sync-D: 9.482 -> 6.670Improved
add predicted-mask injection instead of global audio (ablation)InterActHuman · Multi-Person Test Set (full-body)FVD: 33.895 -> 22.881Improved
add predicted dynamic mask instead of fixed mask (ablation)InterActHuman · Multi-Person Test Set (full-body)FVD: 40.239 -> 22.881Improved
add predicted dynamic mask instead of fixed mask (ablation)InterActHuman · Multi-Person Test Set (full-body)Sync-D: 7.068 -> 6.670Improved
add explicit predicted mask instead of learnable ID embedding (ablation)InterActHuman · Multi-Person Test Set (full-body)Sync-D: 8.627 -> 6.670Improved
add explicit predicted mask instead of learnable ID embedding (ablation)InterActHuman · Multi-Person Test Set (full-body)FVD: 35.665 -> 22.881Improved
add predicted mask instead of global audio (ablation)InterActHuman · Multi-Person Test Set (full-body)IQA: 4.768 -> 4.757No clear effect
add mask cache from previous denoising step (ablation)InterActHuman · Multi-person lip sync (high motion)Sync-D: 11.046 -> 6.921Improved
combine masks across layers instead of layer 4 only (step 50) (ablation)InterActHuman · Low motion mask IoUmask IoU: 0.858 -> 0.956Improved
more denoising steps for mask refinement (step 1 to step 50)InterActHuman combined mask · Low motion mask IoUmask IoU: 0.376 -> 0.956Improved
more denoising steps for mask refinement (step 1 to step 50)InterActHuman combined mask · High motion mask IoUmask IoU: 0.741 -> 0.937Improved
scale from <=3 to 4-5 peopleInterActHuman · Scaling beyond three peopleSync-D: 6.670 -> 6.608No clear effect

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