Research map / Video / Video generation
Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation
Qingxuan Wu, Zhiyang Dou, chuan guo, Yiming Huang, Qiao Feng, Bing Zhou, Jian Wang, Lingjie 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 |
|---|---|---|---|
| fine-tune on filtered InterCompose synthetic data (ablation) | InterActor · InterHuman test | FID: 5.701 -> 5.191 | Improved |
| fine-tune on filtered InterCompose synthetic data (ablation) | InterActor · InterHuman test | R-Precision Top-1: 0.485 -> 0.483 | No clear effect |
| raise filter lower radius d_min from 0.25 to 0.35 (ablation) | InterCompose filtering · InterHuman test | FID: 5.981 -> 5.191 | Improved |
| add word-level conditioning instead of sentence-level AdaLN (ablation) | InterActor · InterHuman test | FID: 5.877 -> 5.701 | Improved |
| add word-level conditioning instead of sentence-level AdaLN (ablation) | InterActor · InterHuman test | R-Precision Top-1: 0.484 -> 0.485 | Improved |
| add adaptive interaction loss instead of flat distance map loss (ablation) | InterActor · InterHuman test | FID: 6.192 -> 5.701 | Improved |
| add all three components (WLC, AIL, FT) (ablation) | InterActor · InterHuman test | FID: 6.237 -> 5.191 | Improved |
| add all three components (WLC, AIL, FT) (ablation) | InterActor · InterHuman test | R-Precision Top-1: 0.441 -> 0.483 | Improved |
| word-level conditioning and adaptive loss vs InterMask | InterActor · InterHuman test | R-Precision Top-1: 0.449 -> 0.483 | Improved |
| InterActor vs InterMask | InterActor · InterHuman test | FID: 5.154 vs 5.191 | No clear effect |
| InterActor vs prior methods | InterActor · InterHuman test | MModality: 1.737 (InterMask) -> 1.051 | Hurt |
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 3 of 4 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
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.91)
- InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint (NeurIPS 2024 · similarity 0.89)
- Learning to Generate Human-Human-Object Interactions from Textual Descriptions (NeurIPS 2025 · similarity 0.89)
- BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics (CVPR 2024 · similarity 0.89)
- HumanTOMATO: Text-aligned Whole-body Motion Generation (ICML 2024 · similarity 0.88)
- Generating Human Motion in 3D Scenes from Text Descriptions (CVPR 2024 · 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.
