A free, multiplatform SDK for real-time facial motion capture using blendshapes, and rigid head pose in 3D space from any RGB camera, photo, or video.

Last update: Dec 27, 2022

Overview

mocap4face by Facemoji

mocap4face by Facemoji is a free, multiplatform SDK for real-time facial motion capture based on Facial Action Coding System or (FACS). It provides real-time FACS-derived blendshape coefficients, and rigid head pose in 3D space from any mobile camera, webcam, photo, or video enabling live animation of 3D avatars, digital characters, and more.

After fetching the input from one of the mentioned sources, mocap4face SDK produces data in ARKit-compatible blendshapes, i.e., morph targets weight values as a per-frame expression shown in the video below. Useful for, e.g., animating a 2D or 3D avatar in a way that mimics the user's facial expressions in real-time à la Apple Memoji but without the need of a hardware-based TrueDepth Camera.

With mocap4face, you can drive live avatars, build Snapchat-like lenses, AR experiences, face filters that trigger actions, VTubing apps, and more with as little energy impact and CPU/GPU use as possible. As an example, check out how the popular avatar live-streaming app REALITY is using our SDK.

Please ⭐ Star us on GitHub—it motivates us a lot!

📋 Table of Content

Tech Specs
Installation
Use Cases
License
Links

🤓 Tech Specs

iOS, Android, Web (coming soon)
3D reprojection to the input photo/video
Platform-suited API and packaging with internal optimizations
Simultaneous back and front camera support

✨ Key Features

42 tracked facial expressions via blendshapes
Eye tracking including eye gaze vector
Tongue tracking
Light & fast, just 3MB ML model size
≤ ±50° pitch, ≤ ±40° yaw and ≤ ±30° roll tracking coverage

🤳 Input

All RGB camera
Photo
Video

📦 Output

ARKit-compatible blendshapes
Head position and scale in 2D and 3D
Head rotation in world coordinates

⚡ Performance

50 FPS on Pixel 4
60 FPS on iPhone SE (1st gen)
90 FPS on iPhone X or newer

💿 Installation

Prerequisites

Get a new developer account at studio.facemoji.co
Generate a unique API key for your app
Paste the API key to your source code

iOS

Open the sample XCode project and run the demo on your iOS device
To use the SDK in your project, either use the bundled XCFramework directly or use the Swift Package manager (this repository also serves as a Swift PM repository)

Android

Open the sample project in Android Studio and run the demo on your Android device
Add this repository to the list of your Maven repositories in your root build.gradle, for example:

allprojects {
    repositories {
        google()
        mavenCentral()
        // Any other repositories here...

        maven {
            name = "Facemoji"
            url = uri("https://facemoji.jfrog.io/artifactory/default-maven-local/")
        }
    }
}

To use the SDK in your project, add implementation 'co.facemoji:mocap4face:0.1.0' to your Gradle dependencies

🚀 Use Cases

Live avatar experiences
Snapchat-like lense
AR experiences
VTubing apps
Live streaming apps
Face filters
AR games with facial triggers
Beauty AR
Virtual try-on
Play to earn games

❤️ Links

📄 License

This library is provided under the Facemoji SDK License Agreement—see LICENSE.

The sample code in this repository is provided under the Facemoji Samples License

Notices

OSS used in mocap4face SDK:

Comments

Mainactivity re-opened cannot be traced
Only the first open MainActivity can be tracked. when back to SplashActivity and reopen Mainactivity the track result is null.

The test code is as follows（modify SplashAtivity）：

override fun onResume() { super.onResume() Timer("Splash", false).schedule(5000) { startMainActivity() } }
bug
opened by cike978 9
can not find any documents about how to build a app using facemoji SDK

i want to build a app like the offical facemoji app, but the demo code is so simple, the SDK even has no document.

can anyone tell me how to use the SDK to build a facemoji app ?

opened by danlanxiaohei 3
Fix "artifact not found for target 'mocap4face'" error
Issue

I got "artifact not found for target 'mocap4face'" error when I tried to load mocap4face Swift Package by Xcode 13.3

The target name should be exactly the same as the framework name (case sensitive)

Changes

Change the target name from mocap4face to Mocap4Face to match the framework name
opened by magicien 2
Any plans for Windows & MacOS Support?

I'm guessing if this is already cross-platform on Android, Web, and iOS that this an upcoming features. Just curious since we'd love to use this everywhere if possible

opened by aaronn 2
[Question]: Is this Lib compatible with react-native?

It would be incredibly awesome to include this library in my React-Native start-up App but I wonder whether there's React-Native compatible SDK?

Thanks!!!
enhancement

opened by shamxeed 2
OpenGLResizer20: setup OES texture: glError 1282: invalid operation

使用 Android 版本打开 Activity 正常，关闭页面再次启用的时候出现 OpenGLResizer20: setup OES texture: glError 1282: invalid operation

onCameraImageArkitLink(cameraTexture: OpenGLTexture)

cameraTexture = null

opened by pengzhenkun 1
Stop face tracking

Hello. Thanks for the great face tracking library!

How can I stop tracking? Something like a dispose/destroy function?

I am using this library in web (js)

opened by Nawarius 1
Status of macOS build?

Has any new work been done to bring this to the Mac via catalyst?

We primarily just want to be able to use the full camera width when running under M1 catalyst. We don't need the full feature-set, but macOS forces "non-mac" frameworks to use a cropped iPhone-like camera view even on the Mac which has a much wider view.

opened by aaronn 0
Problems with one eye open and the other closed

Platform Android With one eye open and the other closed, the output is eyeBlink_L 0.7 and eyeBlink_R 0.5 Expected result is eyeBlink_L 0.7 and eyeBlink_R 0
bug

opened by will4621d 2

Releases(0.3.0)

Owner

Facemoji

Avatars for apps and games.

GitHub Repository

Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight

Revisiting RCAN: Improved Training for Image Super-Resolution Introduction Image super-resolution (SR) is a fast-moving field with novel architectures

76 Dec 01, 2022

Second Order Optimization and Curvature Estimation with K-FAC in JAX.

KFAC-JAX - Second Order Optimization with Approximate Curvature in JAX Installation | Quickstart | Documentation | Examples | Citing KFAC-JAX KFAC-JAX

90 Dec 22, 2022

This code finds bounding box of a single human mouth.

This code finds bounding box of a single human mouth. In comparison to other face segmentation methods, it is relatively insusceptible to open mouth conditions, e.g., yawning, surgical robots, etc. T

4 Nov 27, 2022

Official PyTorch Implementation of Learning Architectures for Binary Networks

Learning Architectures for Binary Networks An Pytorch Implementation of the paper Learning Architectures for Binary Networks (BNAS) (ECCV 2020) If you

25 Jun 09, 2022

NumPy로 구현한 딥러닝 라이브러리입니다. (자동 미분 지원)

Deep Learning Library only using NumPy 본 레포지토리는 NumPy 만으로 구현한 딥러닝 라이브러리입니다. 자동 미분이 구현되어 있습니다. 자동 미분 자동 미분은 미분을 자동으로 계산해주는 기능입니다. 아래 코드는 자동 미분을 활용해 역전파

17 Aug 16, 2022

Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds

Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds Xinxin Zuo, Sen Wang, Minglun Gong, Li Cheng Prerequisites We have tested the code on Ubun

41 Dec 12, 2022

Learning cell communication from spatial graphs of cells

ncem Features Repository for the manuscript Fischer, D. S., Schaar, A. C. and Theis, F. Learning cell communication from spatial graphs of cells. 2021

77 Dec 30, 2022

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

SfMLearner This codebase implements the system described in the paper: Unsupervised Learning of Depth and Ego-Motion from Video Tinghui Zhou, Matthew

1.8k Dec 30, 2022

Yolov5 deepsort inference，使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中

使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中。

813 Dec 31, 2022

Tensorflow implementation of ID-Unet: Iterative Soft and Hard Deformation for View Synthesis.

ID-Unet: Iterative-view-synthesis(CVPR2021 Oral) Tensorflow implementation of ID-Unet: Iterative Soft and Hard Deformation for View Synthesis. Overvie

17 Aug 23, 2022

PyTorch implementation of federated learning framework based on the acceleration of global momentum

Federated Learning with Acceleration of Global Momentum PyTorch implementation of federated learning framework based on the acceleration of global mom

0 Dec 23, 2021

The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

Action Transformer A Self-Attention Model for Short-Time Human Action Recognition This repository contains the official TensorFlow implementation of t

20 Jan 03, 2023

Matching python environment code for Lux AI 2021 Kaggle competition, and a gym interface for RL models.

Lux AI 2021 python game engine and gym This is a replica of the Lux AI 2021 game ported directly over to python. It also sets up a classic Reinforceme

74 Nov 03, 2022

A collection of awesome resources image-to-image translation.

awesome image-to-image translation A collection of resources on image-to-image translation. Contributing If you think I have missed out on something (

876 Dec 28, 2022

A mini library for Policy Gradients with Parameter-based Exploration, with reference implementation of the ClipUp optimizer from NNAISENSE.

PGPElib A mini library for Policy Gradients with Parameter-based Exploration [1] and friends. This library serves as a clean re-implementation of the

56 Jan 01, 2023