Code for our ICCV 19 Paper : Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking, available here : https://arxiv.org/abs/1904.01324
- pytorch 1.0.0
- h5py 2.8.0
- matplotlib 3.0.2
- Clone this repository.
- 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.
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]
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.
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.
If you use this code, please cite our work :
@InProceedings{Sharma_2019_ICCV,
author = {Sharma, Saurabh and Varigonda, Pavan Teja and Bindal, Prashast and Sharma, Abhishek and Jain, Arjun},
title = {Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}