1. MIDGET: Music Conditioned 3D Dance Generation
- Author
-
Wang, Jinwu, Mao, Wei, and Liu, Miaomiao
- Subjects
Computer Science - Sound ,Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Graphics ,Electrical Engineering and Systems Science - Audio and Speech Processing - Abstract
In this paper, we introduce a MusIc conditioned 3D Dance GEneraTion model, named MIDGET based on Dance motion Vector Quantised Variational AutoEncoder (VQ-VAE) model and Motion Generative Pre-Training (GPT) model to generate vibrant and highquality dances that match the music rhythm. To tackle challenges in the field, we introduce three new components: 1) a pre-trained memory codebook based on the Motion VQ-VAE model to store different human pose codes, 2) employing Motion GPT model to generate pose codes with music and motion Encoders, 3) a simple framework for music feature extraction. We compare with existing state-of-the-art models and perform ablation experiments on AIST++, the largest publicly available music-dance dataset. Experiments demonstrate that our proposed framework achieves state-of-the-art performance on motion quality and its alignment with the music., Comment: 12 pages, 6 figures Published in AI 2023: Advances in Artificial Intelligence
- Published
- 2024
- Full Text
- View/download PDF