Research map / Video / Video generation
Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation
Shaowei Liu, Chuan Guo, Bing Zhou, Jian Wang
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 interactive pose anchoring (ablation) | Ponimator pose animator · Inter-X pose animation | FID: 7.1 -> 5.0 | Improved |
| add interactive pose anchoring (ablation) | Ponimator pose animator · Dual-Human pose animation | FID: 36.9 -> 24.2 | Improved |
| add interaction time encoding (ablation) | Ponimator pose animator · Inter-X pose animation | FID: 6.3 -> 5.0 | Improved |
| add interaction time encoding (ablation) | Ponimator pose animator · Dual-Human pose animation | FID: 30.3 -> 24.2 | Improved |
| add joints condition encoding (ablation) | Ponimator pose animator · Inter-X pose animation | FID: 5.6 -> 5.0 | Improved |
| add joints condition encoding (ablation) | Ponimator pose animator · Dual-Human pose animation | FID: 29.9 -> 24.2 | Improved |
| use interactive frames instead of random frames as anchor (ablation) | Ponimator pose animator · Inter-X pose animation | FID: 5.8 -> 5.0 | Improved |
| use interactive frames instead of random frames as anchor (ablation) | Ponimator pose animator · Dual-Human pose animation | FID: 30.1 -> 24.2 | Improved |
| anchor on interactive poses for unconstrained generation vs InterGen | Ponimator · Inter-X unconstrained synthesis | FID: 56.6 -> 22.6 | Improved |
| add interactive pose anchor (ablation) | Ponimator · Inter-X text-to-interaction | FID: 2.74 -> 1.82 | Improved |
| add interactive pose anchor (ablation) | Ponimator · Inter-X single pose-to-interaction | FID: 40.0 -> 27.8 | Improved |
| add interactive pose anchor (ablation) | Ponimator · Inter-X single pose-to-interaction | contact ratio: 67.5 -> 73.3 | Improved |
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.
- InterGen — InterGen: Diffusion-Based Multi-human Motion Generation Under Complex Interactions (IJCV 2024) · better on 5 of 6 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
- Capturing Closely Interacted Two-Person Motions with Reaction Priors (CVPR 2024 · similarity 0.90)
- Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning (CVPR 2025 · similarity 0.89)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.89)
- HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models (CVPR 2024 · similarity 0.87)
- MotionMap: Representing Multimodality in Human Pose Forecasting (CVPR 2025 · similarity 0.87)
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.
