Saved in:
Bibliographic Details
Main Authors: Zhang, Xiaotang, Chang, Ziyi, Men, Qianhui, Shum, Hubert
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.09704
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912480689651712
author Zhang, Xiaotang
Chang, Ziyi
Men, Qianhui
Shum, Hubert
author_facet Zhang, Xiaotang
Chang, Ziyi
Men, Qianhui
Shum, Hubert
contents We propose a real-time method for reactive motion synthesis based on the known trajectory of input character, predicting instant reactions using only historical, user-controlled motions. Our method handles the uncertainty of future movements by introducing an intention predictor, which forecasts key joint intentions to make pose prediction more deterministic from the historical interaction. The intention is later encoded into the latent space of its reactive motion, matched with a codebook which represents mappings between input and output. It samples a categorical distribution for pose generation and strengthens model robustness through adversarial training. Unlike previous offline approaches, the system can recursively generate intentions and reactive motions using feedback from earlier steps, enabling real-time, long-term realistic interactive synthesis. Both quantitative and qualitative experiments show our approach outperforms other matching-based motion synthesis approaches, delivering superior stability and generalizability. In our method, user can also actively influence the outcome by controlling the moving directions, creating a personalized interaction path that deviates from predefined trajectories.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09704
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-time and Controllable Reactive Motion Synthesis via Intention Guidance
Zhang, Xiaotang
Chang, Ziyi
Men, Qianhui
Shum, Hubert
Graphics
We propose a real-time method for reactive motion synthesis based on the known trajectory of input character, predicting instant reactions using only historical, user-controlled motions. Our method handles the uncertainty of future movements by introducing an intention predictor, which forecasts key joint intentions to make pose prediction more deterministic from the historical interaction. The intention is later encoded into the latent space of its reactive motion, matched with a codebook which represents mappings between input and output. It samples a categorical distribution for pose generation and strengthens model robustness through adversarial training. Unlike previous offline approaches, the system can recursively generate intentions and reactive motions using feedback from earlier steps, enabling real-time, long-term realistic interactive synthesis. Both quantitative and qualitative experiments show our approach outperforms other matching-based motion synthesis approaches, delivering superior stability and generalizability. In our method, user can also actively influence the outcome by controlling the moving directions, creating a personalized interaction path that deviates from predefined trajectories.
title Real-time and Controllable Reactive Motion Synthesis via Intention Guidance
topic Graphics
url https://arxiv.org/abs/2507.09704