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.

介绍了一种名为 MIDGET 的音乐条件化 3D 舞蹈生成模型，基于舞蹈动作向量量化变分自编码器（VQ-VAE）模型和动作生成预训练（GPT）模型，以生成与音乐节奏相匹配的充满活力且高质量的舞蹈。通过引入三个新组件：1）基于 Motion VQ-VAE 模型的预训练记忆代码本，用于存储不同的人体姿势代码，2）利用 Motion GPT 模型通过音乐和动作编码器生成姿势代码，3）一个用于音乐特征提取的简单框架。通过与现有最先进模型进行比较，并在 AIST++（最大的公开音乐舞蹈数据集）上进行消融实验，实验证明我们提出的框架在运动质量和与音乐的协调性方面实现了最先进的性能。