Research map / Video / Video generation
Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models
Pablo Ruiz-Ponce, Sergio Escalera, José García-Rodríguez, Jiankang Deng, Rolandos Alexandros Potamias
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 |
|---|---|---|---|
| use autoregressive generation with Mixed Memory instead of non-autoregressive (ablation) | Interact2Ar · Inter-X full body | FID: 0.556 -> 0.277 | Improved |
| use autoregressive generation (ablation) | Interact2Ar · Inter-X full body | AUJ (smoothness): 54.97 -> 8.837 | Improved |
| add dedicated hands/body/trajectory heads with cooperative denoiser | Interact2Ar vs InterMask · Inter-X hands only | FID: 1.960 -> 0.906 (non-AR) | Improved |
| increase regular memory from 15 to 90 frames (ablation) | Interact2Ar autoregressive · Inter-X full body | FID: 0.283 -> 0.412 | Hurt |
| add Mixed Memory (short plus downsampled long-term) at 60-frame context (ablation) | Interact2Ar autoregressive · Inter-X full body | FID: 0.316 (60 regular) -> 0.277 (24 frames) | Improved |
| extend Mixed Memory long-term window from 45 to 105 (ablation) | Interact2Ar · Inter-X full body | FID: 0.277 -> 0.325 | No clear effect |
| retrain evaluator on global joint positions | Inter-X evaluator · noise on trajectory only | FID: 0.122 -> 62.05 | Improved |
Later papers that compared with this method
1 later accepted paper reports Interact2Ar as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions (ECCV 2026 · better on 1 of 2 shared results)
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.
- InterMask — InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling (ICLR 2025) · better on 5 of 5 shared results
- InterGen — InterGen: Diffusion-Based Multi-human Motion Generation Under Complex Interactions (IJCV 2024) · better on 4 of 4 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
- InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint (NeurIPS 2024 · similarity 0.90)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.90)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.90)
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.90)
- Auto-Regressive Diffusion for Generating 3D Human-Object Interactions (AAAI 2025 · similarity 0.89)
- TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation (CVPR 2025 · similarity 0.89)
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.
