# jeeliz/jeelizfacefilter

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/jeeliz-jeelizfacefilter).**

2,883 stars · 548 forks · JavaScript · apache-2.0

## Links

- GitHub: https://github.com/jeeliz/jeelizFaceFilter
- Homepage: https://jeeliz.com
- awesome-repositories: https://awesome-repositories.com/repository/jeeliz-jeelizfacefilter.md

## Topics

`3d` `augmented-reality` `camera` `deep-learning` `detection` `face` `face-detect` `face-detection` `face-filters` `face-tracking` `faceswap` `javascript` `lightweight` `multiple-faces` `snapchat` `threejs` `tracking` `webar` `webgl`

## Description

jeelizFaceFilter is a browser-based computer vision engine and WebGL face tracking library designed for AR filters and real-time facial movement tracking. It functions as a neural network face detector that identifies multiple faces and monitors mouth movements and rotation within a web browser.

The system distinguishes itself through a model-swappable detection pipeline, allowing the exchange of neural network weights to balance accuracy and performance across different camera angles and devices. It features real-time lighting synchronization to match the illumination of 3D overlays with the user's environment and generative AI capabilities to create 3D product models from images.

The library covers a broad range of capabilities, including GPU-accelerated rendering for virtual try-on experiences, coordinate-based asset mapping for 3D content integration, and execution state control to manage GPU resource consumption. It also provides tools for video input configuration, including camera resolution and device selection.

## Tags

### Graphics & Multimedia

- [Neural Face Renderers](https://awesome-repositories.com/f/graphics-multimedia/real-time-neural-renderers/neural-face-renderers.md) — Renders lifelike 3D models onto detected faces using synchronized lighting for seamless integration. ([source](https://jeeliz.com))
- [Digital Face Filters](https://awesome-repositories.com/f/graphics-multimedia/digital-face-filters.md) — Overlays 3D models and virtual assets onto detected faces with synchronized lighting and coordinates.
- [GPU-Accelerated Media Rendering](https://awesome-repositories.com/f/graphics-multimedia/gpu-accelerated-media-rendering.md) — Processes 3D overlays and visual effects using the GPU to maintain high frame rates on the web.
- [Environmental Lighting Estimation](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/lighting-systems/3d-lighting-models/environmental-lighting-estimation.md) — Calculates light source direction and intensity from video input to apply matching shaders to 3D objects.
- [Real-Time Motion Tracking](https://awesome-repositories.com/f/graphics-multimedia/real-time-motion-tracking.md) — Monitors facial rotation and mouth movements in a video stream for interactive digital overlays.
- [Dynamic Lighting Synchronization](https://awesome-repositories.com/f/graphics-multimedia/real-time-neural-renderers/dynamic-lighting-synchronization.md) — Matches the lighting of 3D overlays to the user's face in real time for realistic visual integration. ([source](https://jeeliz.com/blog/creating-a-snapchat-like-filter-with-jeelizs-facefilter-api-part-1-creating-your-first-filter/))
- [3D Asset Integrations](https://awesome-repositories.com/f/graphics-multimedia/3d-asset-integrations.md) — Enables connecting facial tracking data to external engines or web APIs to render virtual objects onto faces. ([source](https://cdn.jsdelivr.net/gh/jeeliz/jeelizfacefilter@master/README.md))

### Artificial Intelligence & ML

- [Augmented Reality Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/augmented-reality-frameworks.md) — Renders 3D objects and virtual assets onto a user's face through a web browser.
- [Face Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/facial-analysis-systems/face-detection.md) — Identifies and tracks several unique faces simultaneously within a single video stream. ([source](https://cdn.jsdelivr.net/gh/jeeliz/jeelizfacefilter@master/README.md))
- [Face Tracking](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/facial-analysis-systems/face-tracking.md) — Monitors face rotation and mouth opening in real time to provide coordinates for AR overlays. ([source](https://cdn.jsdelivr.net/gh/jeeliz/jeelizfacefilter@master/README.md))
- [WebGL](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/facial-analysis-systems/face-tracking/webgl.md) — Uses WebGL and neural networks to track facial movement and rotation in real time within a browser.
- [Face Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/face-detection.md) — Provides a configurable detection system that allows swapping models to balance performance and accuracy.
- [Web-Based Computer Vision](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/computer-vision/web-based-computer-vision.md) — Implements client-side face detection and movement monitoring directly within a web browser.
- [Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-networks.md) — Uses machine learning models to locate faces and extract landmarks from a live video stream in real time.
- [3D Asset Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models/3d-asset-generators.md) — Automatically creates detailed 3D product models from images and product pages using generative AI. ([source](https://jeeliz.com/blog/creating-a-snapchat-like-filter-with-jeelizs-facefilter-api-part-1-creating-your-first-filter/))
- [Inference Performance Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-performance-optimization.md) — Adjusts face detection models to balance processing speed and accuracy based on camera angles or device performance. ([source](https://cdn.jsdelivr.net/gh/jeeliz/jeelizfacefilter@master/README.md))
- [Model Weight Swapping](https://awesome-repositories.com/f/artificial-intelligence-ml/model-capability-extensions/ai-provider-interfaces/hot-swappable-providers/model-weight-swapping.md) — Allows switching between different neural network weights to optimize for specific camera angles or device performance.

### User Interface & Experience

- [Facial Landmark Mapping](https://awesome-repositories.com/f/user-interface-experience/coordinate-mapping/facial-landmark-mapping.md) — Maps detected facial landmarks to a 3D coordinate system to align virtual objects with facial movements.
- [Virtual Try-On Interfaces](https://awesome-repositories.com/f/user-interface-experience/virtual-try-on-interfaces.md) — Allows users to see how 3D product models look on their face using real-time tracking and lighting.