Git Product home page Git Product logo

ordinal-pose3d's Introduction

Ordinal Depth Supervision for 3D Human Pose Estimation

Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis

This is the code for the paper Ordinal Depth Supervision for 3D Human Pose Estimation. Please follow the links to read the paper and visit the corresponding project page.

We provide code to test our model on Human3.6M. Please follow the instructions below to setup and use our code. The typical procedure is 1) apply the ConvNet models using a torch script through command line and then 2) run a MATLAB script (from folder matlab) for visualization or evaluation. To run this code, make sure the following are installed:

We will soon update this repository with the training code.

1) Downloading models and data

We provide our models pretrained for Human3.6M. To get the models and the Human3.6M data to reproduce our results on this dataset, please run the following script (be careful, since the size is over 8GB)

bash data.sh

2) Evaluation on Human3.6M (sample)

We have provided a sample of Human3.6M images, following previous work. You can apply our model on this sample by running the command:

th main.lua h36m-sample

Then, to visualize the output, you can use the MATLAB script:

demoH36M.m

3) Evaluation on Human3.6M (full)

If you want to reproduce the results of our paper for Human3.6M, you need to download the full set of images we used for testing, by running the script data.sh as indicated above. These images are extracted from the videos of the original dataset, and correspond to the images used for testing by the most typical protocol. Please check the file:

data/h36m/annot/valid_images.txt

for the correspondence of images with the original videos.

Having downloaded the necessary images, to apply our model on the whole set of Human3.6M images, you can run:

th main.lua h36m

Then, to conclude the evaluation, you need to run the next MATLAB script:

evalH36M.m

This will print the output in a results.txt file.

Citing

If you find this code useful for your research, please consider citing the following paper:

@Inproceedings{pavlakos2018ordinal,
  Title          = {Ordinal Depth Supervision for 3{D} Human Pose Estimation},
  Author         = {Pavlakos, Georgios and Zhou, Xiaowei and Daniilidis, Kostas},
  Booktitle      = {Computer Vision and Pattern Recognition (CVPR)},
  Year           = {2018}
}

Acknowledgements

This code follows closely the released code for the Stacked Hourglass networks by Alejandro Newell. If you use this code, please consider citing the respective paper.

ordinal-pose3d's People

Contributors

geopavlakos avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.