AI Paper Atlas

Research map / Video / Video generation

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Gaojie Lin, Jianwen Jiang, Jiaqi Yang, Zerong Zheng, Chao Liang, Yuan Zhang, Jingtuo Liu

ICCV 2025 · Video › Video generation · approach: Diffusion-based human image animation · 122 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 all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · CyberHost test setFVD: 45.77 -> 31.15Improved
add all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · CyberHost test setFID: 38.38 -> 33.27Improved
add all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · CelebV-HQFVD: 47.86 -> 43.74Improved
add all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · RAVDESSFVD: 18.83 -> 15.13Improved
add all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · CyberHost test setSync-C: 6.465 -> 6.938Improved
add small amount (25%) of text-conditioned data (ablation)OmniHuman · CyberHost test setSync-C: 6.465 -> 5.039Hurt
add all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · CelebV-HQIQA: 3.855 -> 3.644Hurt
add all text-conditioned data (100% vs 0% T-Data) (ablation)OmniHuman · CyberHost test setHKV: 35.82 -> 43.54Improved
introduce pose before audio (IPA) instead of audio only (IA) (ablation)OmniHuman · CyberHost test setFVD: 31.15 -> 36.03Hurt
introduce pose before audio (IPA) instead of audio only (IA) (ablation)OmniHuman · CyberHost test setSync-C: 6.938 -> 4.879Hurt
add pose last (IAP, A>P) after audio training (ablation)OmniHuman · CyberHost test setFVD: 31.15 -> 31.08No clear effect
add pose last (IAP, A>P) after audio training (ablation)OmniHuman · CyberHost test setSync-C: 6.938 -> 6.951No clear effect

Later papers that compared with this method

3 later accepted papers report OmniHuman-1 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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