Saved in:
Bibliographic Details
Main Authors: 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
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!
Table of 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.