Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
This repository is the PyTorch implementation for the network presented in:
Xingyi Zhou, Qixing Huang, Xiao Sun, Xiangyang Xue, Yichen Wei, Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach ICCV 2017 (arXiv:1704.02447)
Checkout the original torch implementation.
Checkout the clean 2D hourglass network branch.
Contact: zhouxy2017@gmail.com
Requirements
Testing
We provide example images in 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.
Training
python main.py -expID Stage1
Our results of this stage is provided here.
python main.py -expID Stage2 -ratio3D 1 -regWeigh 0.1 -loadModel ../exp/Stage1/model_60.pth -nEpochs 30 -dropLR 25
python main.py -expID Stage3 -ratio3D 1 -regWeigh 0.1 -varWeight 0.01 -loadModel ../exp/Stage2/model_30.pth -LR 2.5e-5 -nEpochs 10
Citation
@InProceedings{Zhou_2017_ICCV,
author = {Zhou, Xingyi and Huang, Qixing and Sun, Xiao and Xue, Xiangyang and Wei, Yichen},
title = {Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}