GTA-Human II
收藏GTA-Human 数据集工具箱
数据集概述
数据集列表
| 特性 | GTA-Human | GTA-Human II |
|---|---|---|
| 场景数量 | 20,005 | 10,224 |
| 人物序列数量 | 20,005 | 35,352 |
| 彩色图像 | 是 | 是 |
| 3D 边界框 & 点云 | 否 | 是 |
| 参数化模型 | SMPL | SMPL-X |
| 每场景中的人物数量 | 1 | 1-6 |
数据集更新
- [2024-09-19] GTA-Human II 数据集发布
- [2022-07-08] GTA-Human 数据集在 MMHuman3D 上发布
安装指南
可视化工具安装
bash conda create -n gta-human python=3.9 -y conda activate gta-human pip install torch==1.12.1 opencv-python==4.10.0.84 smplx==0.1.28 chumpy==0.70 trimesh==4.4.3 tqdm==4.66.4 numpy==1.23.1 pyrender==0.1.45
文件下载工具安装
bash pip install openxlab
GTA-Human II 可视化工具安装
bash pip install open3d==0.14.1
引用
text @ARTICLE{10652891, author={Cai, Zhongang and Zhang, Mingyuan and Ren, Jiawei and Wei, Chen and Ren, Daxuan and Lin, Zhengyu and Zhao, Haiyu and Yang, Lei and Loy, Chen Change and Liu, Ziwei}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, title={Playing for 3D Human Recovery}, year={2024}, volume={}, number={}, pages={1-12}, keywords={Three-dimensional displays;Annotations;Synthetic data;Shape;Training;Parametric statistics;Solid modeling;Human Pose and Shape Estimation;3D Human Recovery;Parametric Humans;Synthetic Data;Dataset}, doi={10.1109/TPAMI.2024.3450537} }




