Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.13082 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917338891157504 |
|---|---|
| author | Yang, Yebin Wen, Di Qi, Lei Kong, Weitong Zheng, Junwei Liu, Ruiping Chen, Yufan Wu, Chengzhi Yang, Kailun Fu, Yuqian Paudel, Danda Pani Van Gool, Luc Peng, Kunyu |
| author_facet | Yang, Yebin Wen, Di Qi, Lei Kong, Weitong Zheng, Junwei Liu, Ruiping Chen, Yufan Wu, Chengzhi Yang, Kailun Fu, Yuqian Paudel, Danda Pani Van Gool, Luc Peng, Kunyu |
| contents | Text-guided 3D motion editing has seen success in single-person scenarios, but its extension to multi-person settings is less explored due to limited paired data and the complexity of inter-person interactions. We introduce the task of multi-person 3D motion editing, where a target motion is generated from a source and a text instruction. To support this, we propose InterEdit3D, a new dataset with manual two-person motion change annotations, and a Text-guided Multi-human Motion Editing (TMME) benchmark. We present InterEdit, a synchronized classifier-free conditional diffusion model for TMME. It introduces Semantic-Aware Plan Token Alignment with learnable tokens to capture high-level interaction cues and an Interaction-Aware Frequency Token Alignment strategy using DCT and energy pooling to model periodic motion dynamics. Experiments show that InterEdit improves text-to-motion consistency and edit fidelity, achieving state-of-the-art TMME performance. The dataset and code will be released at https://github.com/YNG916/InterEdit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13082 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing Yang, Yebin Wen, Di Qi, Lei Kong, Weitong Zheng, Junwei Liu, Ruiping Chen, Yufan Wu, Chengzhi Yang, Kailun Fu, Yuqian Paudel, Danda Pani Van Gool, Luc Peng, Kunyu Computer Vision and Pattern Recognition Robotics Image and Video Processing Text-guided 3D motion editing has seen success in single-person scenarios, but its extension to multi-person settings is less explored due to limited paired data and the complexity of inter-person interactions. We introduce the task of multi-person 3D motion editing, where a target motion is generated from a source and a text instruction. To support this, we propose InterEdit3D, a new dataset with manual two-person motion change annotations, and a Text-guided Multi-human Motion Editing (TMME) benchmark. We present InterEdit, a synchronized classifier-free conditional diffusion model for TMME. It introduces Semantic-Aware Plan Token Alignment with learnable tokens to capture high-level interaction cues and an Interaction-Aware Frequency Token Alignment strategy using DCT and energy pooling to model periodic motion dynamics. Experiments show that InterEdit improves text-to-motion consistency and edit fidelity, achieving state-of-the-art TMME performance. The dataset and code will be released at https://github.com/YNG916/InterEdit. |
| title | InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing |
| topic | Computer Vision and Pattern Recognition Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2603.13082 |