Style-ERD: Responsive and Coherent Online Motion Style Transfer

Autor:	Tao, Tianxin, Zhan, Xiaohang, Chen, Zhongquan, van de Panne, Michiel
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Motion style transfer is a common method for enriching character animation. Motion style transfer algorithms are often designed for offline settings where motions are processed in segments. However, for online animation applications, such as realtime avatar animation from motion capture, motions need to be processed as a stream with minimal latency. In this work, we realize a flexible, high-quality motion style transfer method for this setting. We propose a novel style transfer model, Style-ERD, to stylize motions in an online manner with an Encoder-Recurrent-Decoder structure, along with a novel discriminator that combines feature attention and temporal attention. Our method stylizes motions into multiple target styles with a unified model. Although our method targets online settings, it outperforms previous offline methods in motion realism and style expressiveness and provides significant gains in runtime efficiency Comment: CVPR 2022, project page: https://tianxintao.github.io/Online-Motion-Style-Transfer
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.02574 Zobrazit plný text záznamu View this record from Arxiv