Skip to content

cbiras/3DHPose

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

3DHPose

3DHPose is an improved version of mvpose.

Installation

Please follow the installation and usage steps from the original repo

Purpose

This project aims to estimate multi-person 3D Human poses from multiple views. Because the original repo achieves high accuracy, the main purpose of this project is to speed up the process as much as possible.

Changes

All the backbone networks were changed in order to achieve a better inference time.

Object detector used: CenterNet

ReId module used: OsNet

2D Human pose detector: CPN using only GlobalNet with ResNet50 as the backbone network.

Results

Method Time Accuracy
Original Repo 12:21(min) 96.36%
3DHPose 02:14(min) 96.21%

Both configurations were tested using a Tesla P100 GPU, on Google Colab. The test dataset is the campus one from the original repo.

Citation

@article{dong2019fast,
  title={Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views},
  author={Dong, Junting and Jiang, Wen and Huang, Qixing and Bao, Hujun and Zhou, Xiaowei},
  journal={CVPR},
  year={2019}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published