In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive approaches, including recent diffusion-based approaches. For example, on HumanML3D, which is currently the largest dataset, we achieve comparable performance on the consistency between text and generated motion (R-Precision), but with FID 0.116 largely outperforming MotionDiffuse of 0.630. Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach. Our work suggests that VQ-VAE still remains a competitive approach for human motion generation.

本文研究了基于 VQ-VAE 和 GPT 的人体运动生成的条件生成框架，并表明了通过常用的训练配方（EMA 和 Code Reset），我们可以获得高质量的离散表示。此外，我们在训练期间采用了一种简单的损坏策略来缓解训练 - 测试偏差，并在 HumanML3D 数据集上表现出比竞争方法更好的性能。

T2M-GPT: 使用离散表示生成基于文本描述的人体动作