STyMo: Fast and Controllable Few-Shot Motion Style Transfer

2026-09-03

AI Summary

本文提出STyMo方法，通过少量数据快速学习并转移运动风格，分解静态与动态风格成分以实现可控性。

Abstract

Supporting a wide variety of motion styles is critical for creating diverse virtual characters, but current methods either require large stylized datasets or pre-trained models that cannot generalize beyond their training distribution. We present STyMo, a few-shot approach that learns motion style from only seconds of paired data and trains in one to two minutes. Our key insight is to decompose style into two components: a static component capturing time-invariant posture, and a temporal component capturing frame-wise dynamics. This decomposition yields an interpretable system where posture intensity, temporal exaggeration, and per-body-region style can be adjusted at runtime. Furthermore, the reduction in required training data and computation time structurally permits an iterative authoring workflow. To ensure robustness on arbitrary inputs, we further introduce a stylizability gate that automatically prevents artifacts on out-of-distribution motions. We demonstrate results across diverse motion styles, from subtle emotional variations to exaggerated character archetypes, and release our processed paired dataset to facilitate future research.

Problem

• motion style transfer
• few-shot learning
• stylized datasets
• generalization
• diverse virtual characters

Innovation

• few-shot learning
• motion style transfer
• decomposition of style
• stylizability gate
• iterative authoring workflow