Style-ERD: Responsive and Coherent Online Motion Style Transfer
This work addresses the need for low-latency, high-quality motion style transfer in real-time applications like motion capture for avatars, representing an incremental advance with specific performance gains.
The paper tackled the problem of online motion style transfer for real-time avatar animation, achieving higher motion realism and style expressiveness than previous offline methods while improving runtime efficiency.
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