Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio

Abstract

Synthesizing human motion through learning techniques is becoming an increasingly popular approach to alleviating the requirement of new data capture to produce animations. Learning to move naturally from music, i.e., to dance, is one of the more complex motions humans often perform effortlessly. Each dance movement is unique, yet such movements maintain the core characteristics of the dance style. Most approaches addressing this problem with classical convolutional and recursive neural models undergo training and variability issues due to the non-Euclidean geometry of the motion manifold structure.In this paper, we design a novel method based on graph convolutional networks to tackle the problem of automatic dance generation from audio information. Our method uses an adversarial learning scheme conditioned on the input music audios to create natural motions preserving the key movements of different music styles. We evaluate our method with three quantitative metrics of generative methods and a user study. The results suggest that the proposed GCN model outperforms the state-of-the-art dance generation method conditioned on music in different experiments. Moreover, our graph-convolutional approach is simpler, easier to be trained, and capable of generating more realistic motion styles regarding qualitative and different quantitative metrics. It also presented a visual movement perceptual quality comparable to real motion data.

Accepted at the Elsevier Computers & Graphics (C&G) 2020

References in corpus (7)

• Conditional Generative Adversarial Nets
• On the difficulty of training Recurrent Neural Networks
• WaveNet: A Generative Model for Raw Audio
• Learning to Generate Long-term Future via Hierarchical Prediction
• Video-to-Video Synthesis
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Constructing Human Motion Manifold with Sequential Networks

Cited by in corpus (5)

• Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
• Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video
• DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation
• DanceGen: Supporting Choreography Ideation and Prototyping with Generative AI
• Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism