Step 1: Download Human3.6M from the official website
We use the same COCO format for Human3.6M as PoseNet and I2L-MeshNet.
To generate the format, follow the instructions in the PoseNet repo:
- Run the matlab preprocessing script using the official Human3.6M SDK.
- Run h36m2coco.py:
python h36m2coco.py
- Download the SMPL parameters obtained using gradient-based optimization. Unzip the file into
datasets/smpl_fit
.
The resulting COCO-format Human3.6m dataset will have the following structure:
${GLAMR_ROOT}
|-- datasets
| |-- H36M
| | |-- images
| | |-- annotations
| | |-- smpl_fit
Take the following steps in the root folder of this repo:
- Further process the COCO-format human3.6M dataset:
python preprocess/preprocess_h36m.py
- Generate Dynamic Human3.6M with occlusions:
python preprocess/preprocess_h36m_occluded.py
The resulting Dynamic Human3.6M dataset is stored in datasets/H36M/occluded_v2
.