Avatar Controller Toolkit

The Avatar Controller Toolkit (ACT) is a tool developped to enhance the visualisation of any expression model which would be performed by an agent, Lou, we have created using Blender. The ACT project uses the power of Unity and Blender, mixed in a tool made for the users.

View Wiki · Report Bug

About The Project

Here's a preview of what you will find in that repository. To make it simple, we wanted to create an avatar in a virtual environment that will be able to replay expressions form yourself or your AI Model.

In doing so, we ended creating a video exporter, where you can create a sequence of expression you want the avatar to perform and export it as a MP4 file.

Plus, a Wizard of Oz experiment interface that allows you to perform wizard of oz experiment easely, using a server and a build of the project. If you are not familiar with wizard of oz experiments, please follow this link.

In the future, we want to improve the toolkit's modularity, where you will be able to add your own avatar, use different types of expression, not only .csv, and respond to the need of the scientific community.

This project has highly been inspired by an older project we made in Godoot Engine, find the link here.

(back to top)

Getting Started

Everything you need to know to use the project is precised in the wiki of the repository, find the link here

How does it work ?

The current state of the project supports OpenFace expressions. Which means that if you motion tracking software doesn't output a csv file in the same manner as OpenFace, you won't be able to use this tool.

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you want to contribute to the project, please follow the steps below :

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

To Do

• Create a rewind button to replay a queue we created
• Make a configuration interface to change the avatar

License

See LICENSE for more information.

Contact

Kevin El Haddad - ACT Creator

Armand DEFFRENNES - armand.deffrennes@student.junia.com - ACT Dev

Project Link: Git Repo

(back to top)