Generalizing Stylized Motion Generation Method by Introducing Metadata-Independent Learning and Unified Multiple Motion Dataset
Lists
Only you see this
Abstract
This study aims to extend the applicability of stylized motion generation methods to be robust for large and diverse motions akin to those found in real-world data. Specifically, we introduce metadata-independent learning alongside style-focused learning, thereby enabling training from motions absent in motion-style datasets. In addition, we construct a novel motion dataset containing both various motions and stylized motions by unifying the multiple datasets to effectively train the model. Our novel learning method and dataset enable stylized motion generation methods to learn from both various motion knowledge and motion-style relations and improve their generalized performance. In downstream tasks, we address motion style transfer and text-to-stylized-motion, validating the enhancement of generalization abilities for each task. Compared to conventional methods, the proposed method demonstrates superior performance in generating and reflecting style, particularly under conditions featuring larger and more diverse motions. The code for this paper and the dataset will be released.
BibTeX
@article{era2026generalizing,
author = {Yuki Era and Ren Togo and Keisuke Maeda and Takahiro Ogawa and Miki Haseyama},
title = {{Generalizing Stylized Motion Generation Method by Introducing Metadata-Independent Learning and Unified Multiple Motion Dataset}},
journal = {IEEE Trans. Multimedia},
year = {2026},
doi = {10.1109/tmm.2025.3645612},
}Loading related content...