Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music
This addresses the challenge of creating realistic dance animations for artificial agents and robots, though it appears incremental as it builds on existing generative autoregressive models.
The paper tackles the problem of generating 3D human dance poses from music, resulting in a framework that synthesizes sequences over 5,000 frames and enables a humanoid robot to dance by listening to music.
This paper proposes a framework which is able to generate a sequence of three-dimensional human dance poses for a given music. The proposed framework consists of three components: a music feature encoder, a pose generator, and a music genre classifier. We focus on integrating these components for generating a realistic 3D human dancing move from music, which can be applied to artificial agents and humanoid robots. The trained dance pose generator, which is a generative autoregressive model, is able to synthesize a dance sequence longer than 5,000 pose frames. Experimental results of generated dance sequences from various songs show how the proposed method generates human-like dancing move to a given music. In addition, a generated 3D dance sequence is applied to a humanoid robot, showing that the proposed framework can make a robot to dance just by listening to music.