Emotion Transfer for 3D Hand Motion using StarGAN

In this paper, we propose a new data-driven framework for 3D hand motion emotion transfer. Specifically, we first capture high-quality hand motion using VR gloves. The hand motion data is then annotated with the emotion type and converted to images to facilitate the motion synthesis process and the new dataset will be available to the public. To the best of our knowledge, this is the first public dataset with annotated hand motions. We further formulate the emotion transfer for 3D hand motion as an Image-to-Image translation problem, and it is done by adapting the StarGAN framework. Our new framework is able to synthesize new motions, given target emotion type and an unseen input motion. Experimental results show that our framework can produce high quality and consistent hand motions.