Research map / Video / Video generation
Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning
Zhenwu Shi, Jingyu Gong, Peiwei Wang, Xingzan Wang, Tianwen Qian, Wenxi Li, Yuan Fang, Jiao Xie, Lizhuang Ma, Shaohui Lin
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 retrospective feature supervision (ablation) | base diffusion editor · MotionFix full test set | AvgR: 20.88 -> 18.62 | Improved |
| add triplet semantic alignment loss (ablation) | base diffusion editor · MotionFix full test set | AvgR: 20.88 -> 17.99 | Improved |
| add motion preservation loss (ablation) | base diffusion editor · MotionFix full test set | AvgR: 20.88 -> 15.58 | Improved |
| add retrospective and triplet losses together (ablation) | base diffusion editor · MotionFix full test set | AvgR: 20.88 -> 16.82 | Improved |
| add motion preservation loss to retro + triplet (ablation) | retro + triplet model · MotionFix full test set | AvgR: 16.82 -> 13.06 | Improved |
| add motion preservation loss to retro + triplet (ablation) | retro + triplet model · MotionFix batch | R@1: 74.58 -> 77.29 | Improved |
| add retrospective feature supervision (ablation) | base diffusion editor · MotionFix batch | R@3: 89.58 -> 88.75 | Hurt |
| add triplet loss alone (ablation) | base diffusion editor · MotionFix full test set | R@1: 26.88 -> 28.26 | Mixed |
| full OmniME vs SimMotionEdit* on STANCE | OmniME · STANCE Adjustment test set | AvgR: 29.05 -> 22.77 | Improved |
| full OmniME vs SimMotionEdit* on MotionFix | OmniME · MotionFix test set | AvgR: 20.88 -> 13.06 | Improved |
| train on MotionFix, test on STANCE: OmniME vs SimMotionEdit* | OmniME · Cross-dataset STANCE (batch) | AvgR: 8.80 -> 7.44 | Improved |
| train on MotionFix, test on STANCE: OmniME vs SimMotionEdit* | OmniME · Cross-dataset STANCE (batch) | R@1: 21.43 -> 22.40 | 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.
- SimMotionEdit — SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction (CVPR 2025) · better on 13 of 13 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 0.89)
- Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing (CVPR 2026 · similarity 0.88)
- Dynamic Motion Blending for Versatile Motion Editing (CVPR 2025 · similarity 0.87)
- MMM: Generative Masked Motion Model (CVPR 2024 · similarity 0.86)
- SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing (CVPR 2025 · similarity 0.86)
- OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers (CVPR 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.
