Research map / Video / Video generation
InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing
Yebin Yang, Di Wen, Lei Qi, Weitong Kong, Junwei Zheng, Ruiping Liu, Yufan Chen, Chengzhi Wu, Kailun Yang, Yuqian Fu, Danda Paudel, Luc Van Gool and 1 more
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 plan tokens and frequency tokens (ablation) | InterEdit base diffusion · InterEdit3D test (TMME) | g2t R@1: 24.97 -> 30.82 | Improved |
| add plan tokens and frequency tokens (ablation) | InterEdit base diffusion · InterEdit3D test (TMME) | g2s R@1: 12.54 -> 17.08 | Improved |
| add plan tokens and frequency tokens (ablation) | InterEdit base diffusion · InterEdit3D test (TMME) | FID: 0.4451 -> 0.3707 | Improved |
| add plan token alignment alone (ablation) | InterEdit base diffusion · InterEdit3D test (TMME) | g2t R@3: 40.68 -> 43.50 | Improved |
| add frequency token alignment alone (ablation) | InterEdit base diffusion · InterEdit3D test (TMME) | g2t R@3: 40.68 -> 44.05 | Improved |
| add frequency tokens on top of plan tokens (ablation) | InterEdit · InterEdit3D test (TMME) | g2t R@3: 43.50 -> 47.65 | Improved |
| add frequency tokens on top of plan tokens (ablation) | InterEdit · InterEdit3D test (TMME) | FID: 0.3667 -> 0.3707 | Hurt |
| add plan tokens on top of frequency tokens (ablation) | InterEdit · InterEdit3D test (TMME) | FID: 0.3798 -> 0.3707 | Improved |
| raise frequency-token dropout from 0.03 to 0.05 (ablation) | InterEdit · InterEdit3D test (TMME) (Lp=5, Lf=5) | FID: 0.3693 -> 0.3477 | Improved |
| frequency-token dropout 0.04 vs 0.05 (ablation) | InterEdit · InterEdit3D test (TMME) (Lp=5, Lf=5) | g2t R@1: 30.51 -> 29.10 | Mixed |
| use InterEdit instead of TIMotion | TIMotion · InterEdit3D test (TMME) | g2t R@1: 24.97 -> 30.82 | Improved |
| use InterEdit instead of TIMotion | TIMotion · InterEdit3D test (TMME) | FID: 0.4451 -> 0.3707 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- TIMotion — TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation (CVPR 2025) · better on 8 of 8 shared results
- MotionLab — MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm (ICCV 2025) · better on 7 of 7 shared results
- InterGen — InterGen: Diffusion-Based Multi-human Motion Generation Under Complex Interactions (IJCV 2024) · better on 7 of 7 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
- SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction (CVPR 2025 · similarity 0.91)
- Dynamic Motion Blending for Versatile Motion Editing (CVPR 2025 · similarity 0.89)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.88)
- SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing (CVPR 2025 · similarity 0.87)
- MMM: Generative Masked Motion Model (CVPR 2024 · similarity 0.86)
- CigTime: Corrective Instruction Generation Through Inverse Motion Editing (NeurIPS 2024 · similarity 0.86)
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.
