Giter VIP home page Giter VIP logo

mediapipe-facelandmark-demo's Introduction

Animate 3D avatar face using MediaPipe's face-landmark model.

This project aims to test and demonstrate the capabilities of MediaPipe's new face landmark model, which outputs 52 blendshapes. These blendshapes can be interactively tested with avatars from Ready Player Me, with additional features available for customizing these avatars.

Prerequisites

This project requires Node.js to be installed on your local machine.

Installation

  1. Clone the repository:
    git clone https://github.com/jays0606/mediapipe-facelandmarker-demo.git
  2. Navigate into the project directory:
    cd mediapipe-facelandmarker-demo
  3. Install the necessary dependencies:
    npm install
  4. Run the following command, Open your browser and visit http://localhost:3000 to view the project.
    npm run dev

Built With

This project was created using:

Contact

Jaeho Shin - [email protected]

mediapipe-facelandmark-demo's People

Contributors

jays0606 avatar

Stargazers

 avatar Michael Szmadzinski avatar  avatar Luís Morgado avatar Lucie Choi avatar Cch avatar  avatar  avatar  avatar Yar Dolhushyn avatar halu avatar Ajinkya Puar avatar Mohamed Lotfy avatar  avatar  avatar Wilson Chow avatar mikhail sitnikov avatar C. L. avatar Bipin avatar Diego Auyón avatar Jean-Vincent Roger avatar 成雨 avatar exitsimulation avatar Cory Gross avatar KBΓΓR avatar sean tai avatar Rob Eberhardt avatar  avatar  avatar wangpu avatar EvilCandyBar avatar Kerem Çalışkan avatar Aria F avatar Łukasz Furman avatar Mo Kasiri avatar leeoxiang avatar  avatar David Garcia avatar jay avatar Arif Widipratomo avatar Anas Jaber avatar  avatar Martin Wecke avatar  avatar A'W avatar Federico L. Martin avatar Jonathan Macias Casados avatar Sami Haroon avatar FUZZYW avatar  avatar  avatar Todor Imreorov avatar Qalqi avatar  avatar Jason avatar Jay McGuinness avatar stone.tech avatar Wengyu Zhang avatar Richard Huang avatar Dayoung Seon avatar P avatar  avatar

Watchers

C. L. avatar  avatar

mediapipe-facelandmark-demo's Issues

Hand landmark

Hi,
I tried to take this demo forward with detecting the hands and move the avatar's hands
I have created HandLandmarkManager that is doing the detect and drawLandmarks
But i have difficulties to implement "updateHandsTransforms" (on the same convention as "updateFacialTransforms")
i'm missing the part of connecting the HandLandmarkerResult to the hands bones.
and clue on how to implement?

   updateHandsTransforms = (results: HandLandmarkerResult, flipped = true) => {
    if (!results || !this.isModelLoaded) return;
    if(results.handednesses.length > 0){
      let leftIndex,rightIndex;
      for (const categories of results.handednesses) {
        let { index, score, categoryName } = categories[0];
        if(categoryName.includes("Left")){
          leftIndex = index;
        } else if(categoryName.includes("Right")){
          rightIndex = index;
        }
      }
    }
    const LeftHand = this.scene.getObjectByName("LeftHand");
    LeftHand?.traverse((obj) => {
        //implement left hand control
        console.log(obj);
      });
    return
  };

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.