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.
@article{arxiv.2603.13082,
title = {InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing},
author = {Yebin Yang and Di Wen and Lei Qi and Weitong Kong and Junwei Zheng and Ruiping Liu and Yufan Chen and Chengzhi Wu and Kailun Yang and Yuqian Fu and Danda Pani Paudel and Luc Van Gool and Kunyu Peng},
journal= {arXiv preprint arXiv:2603.13082},
year = {2026}
}
Comments
The dataset and code will be released at https://github.com/YNG916/InterEdit