Skip to content
Code for our ICCV 19 paper : Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
Python
Branch: master
Clone or download
Latest commit fb43e28 Aug 26, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
src first commit Mar 29, 2019
.gitignore first commit Mar 29, 2019
LICENSE Create LICENSE Mar 29, 2019
README.md Update README.md Aug 26, 2019
main.py first commit Mar 29, 2019
opt.py first commit Mar 29, 2019
teaser.png

README.md

generative_pose

Code for our ICCV 19 Paper : Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking, available here : https://arxiv.org/abs/1904.01324

Teaser Image

Dependencies

  • pytorch 1.0.0
  • h5py 2.8.0
  • matplotlib 3.0.2

Setup

  1. Clone this repository.
  2. Download the data from Google Drive and unzip it inside the parent directory. It contains preprocessed ground truth 3D coordinates on Human3.6, and 2D pose + Ordinal Relation detections from our 2DPoseNet/OrdinalNet module.

Running the Code

For training MultiPoseNet, run the following command

python main.py --exp [name of your experiment]

For testing run,

python main.py --exp [name of your experiment] --test --numSamples [num of samples to generate] --load [pre-trained model]

Pre-trained model

We provide a pre-trained model on Google Drive. You can reproduce our results by running the test script with this model and generating 200 samples.

Code Layout

This repository closely follows una_dinosauria's Tensorflow repo for their ICCV 17 paper A Simple Yet Effective Baseline for 3D Pose Estimation, and weigq's Pytorch repo for the same.

Citing

If you use this code, please cite our work :

@article{sharma2019monocular,
  title={Monocular 3d human pose estimation by generation and ordinal ranking},
  author={Sharma, Saurabh and Varigonda, Pavan Teja and Bindal, Prashast and Sharma, Abhishek and Jain, Arjun},
  journal={arXiv preprint arXiv:1904.01324},
  year={2019}
}
You can’t perform that action at this time.