This repository includes code for the network presented in:
Xingyi Zhou, Qixing Huang, Xiao Sun, Xiangyang Xue, Yichen Wei, Weakly-supervised Transfer for 3D Human Pose Estimation in the Wild (arXiv:1704.02447)
The code is developed upon Stacked Hourglass Network.
Contact: zhouxy13@fudan.edu.cn
- cudnn
- Torch7 with hdf5 and image
- Python with h5py and opencv
- Download our pre-trained model and move it to
src
. - Run
th demo.lua /path/to/image
.
We provide example images in src/images/
. For testing your own image, it is important that the person should be at the center of the image and most of the body parts should be within the image.
Coming soon.