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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · CyberHost test set | FVD: 45.77 -> 31.15 | Improved |
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · CyberHost test set | FID: 38.38 -> 33.27 | Improved |
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · CelebV-HQ | FVD: 47.86 -> 43.74 | Improved |
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · RAVDESS | FVD: 18.83 -> 15.13 | Improved |
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · CyberHost test set | Sync-C: 6.465 -> 6.938 | Improved |
| add small amount (25%) of text-conditioned data (ablation) | OmniHuman · CyberHost test set | Sync-C: 6.465 -> 5.039 | Hurt |
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · CelebV-HQ | IQA: 3.855 -> 3.644 | Hurt |
| add all text-conditioned data (100% vs 0% T-Data) (ablation) | OmniHuman · CyberHost test set | HKV: 35.82 -> 43.54 | Improved |
| introduce pose before audio (IPA) instead of audio only (IA) (ablation) | OmniHuman · CyberHost test set | FVD: 31.15 -> 36.03 | Hurt |
| introduce pose before audio (IPA) instead of audio only (IA) (ablation) | OmniHuman · CyberHost test set | Sync-C: 6.938 -> 4.879 | Hurt |
| add pose last (IAP, A>P) after audio training (ablation) | OmniHuman · CyberHost test set | FVD: 31.15 -> 31.08 | No clear effect |
| add pose last (IAP, A>P) after audio training (ablation) | OmniHuman · CyberHost test set | Sync-C: 6.938 -> 6.951 | No 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.
- Instilling an Active Mind in Avatars via Cognitive Simulation (ICLR 2026 · better on 7 of 12 shared results)
- Human-Centric Video Generation via Collaborative Multi-Modal Conditioning (AAAI 2026 · better on 0 of 2 shared results)
- Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation (NeurIPS 2025 · better on 0 of 1 shared result)
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.
- MimicMotion — MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance (ICML 2025) · better on 2 of 2 shared results
- AnimateAnyone — Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024) · better on 2 of 2 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
- OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation (CVPR 2025 · similarity 0.91)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.89)
- VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis (CVPR 2025 · similarity 0.89)
- AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers (CVPR 2025 · similarity 0.89)
- EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation (CVPR 2025 · similarity 0.89)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.88)
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.
