@inproceedings{10.1145/3721238.3730688,
author = {Xu, Wenning and Fan, Shiyu and Henderson, Paul and Ho, Edmond S. L.},
title = {Multi-Person Interaction Generation from Two-Person Motion Priors},
year = {2025},
isbn = {9798400715402},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3721238.3730688},
doi = {10.1145/3721238.3730688},
abstract = {Generating realistic human motion with high-level controls is a crucial task for social understanding, robotics, and animation. With high-quality MOCAP data becoming more available recently, a wide range of data-driven approaches have been presented. However, modelling multi-person interactions still remains a less explored area. In this paper, we present Graph-driven Interaction Sampling, a method that can generate realistic and diverse multi-person interactions by leveraging existing two-person motion diffusion models as motion priors. Instead of training a new model specific to multi-person interaction synthesis, our key insight is to spatially and temporally separate complex multi-person interactions into a graph structure of two-person interactions, which we name the Pairwise Interaction Graph. We thus decompose the generation task into simultaneous single-person motion generation conditioned on one other’s motion. In addition, to reduce artifacts such as interpenetrations of body parts in generated multi-person interactions, we introduce two graph-dependent guidance terms into the diffusion sampling scheme. Unlike previous work, our method can produce various high-quality multi-person interactions without having repetitive individual motions. Extensive experiments demonstrate that our approach consistently outperforms existing methods in reducing artifacts when generating a wide range of two-person and multi-person interactions.},
booktitle = {Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers},
articleno = {113},
numpages = {11},
keywords = {Character Animation, Close Interaction, Deep Learning, Neural Network, Multi-character, Diffusion Model},
location = {
},
series = {SIGGRAPH Conference Papers '25}
}