T2M-GPT

(CVPR 2023) T2M-GPT Pytorch 实现的论文 "T2M-GPT: 使用离散表示从文本描述生成人体动作" [项目页面] [论文] [Notebook 演示] [HuggingFace] [空间演示] [T2M-GPT+] 如果我们的项目对您的研究有所帮助,请考虑引用: ```

@inproceedings{zhang2023generating, title={T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations}, author={Zhang, Jianrong and Zhang, Yangsong and Cun, Xiaodong and Huang, Shaoli and Zhang, Yong and Zhao, Hongwei and Lu, Hongtao and Shen, Xi}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2023}, }

## 1. 可视化结果（更多结果可在我们的[项目页面](https://mael-zys.github.io/T2M-GPT/)中找到）

我们使用两个 3D 人体动作语言数据集: HumanML3D 和 KIT-ML。