Real-time and Controllable Reactive Motion Synthesis via Intention Guidance

TL;DR

This paper introduces a real-time reactive motion synthesis method that predicts and generates character movements based on user input and intentions, enabling interactive and personalized animations with improved stability.

Contribution

It presents a novel intention-guided reactive motion synthesis framework that operates in real-time, incorporating intention prediction and feedback loops for long-term interactive control.

Findings

Outperforms existing matching-based methods in stability and generalizability.

Enables real-time, long-term reactive motion generation with feedback.

Allows user-controlled personalized interaction paths.

Abstract

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.