#168168th of 168 in ML frameworks and libraries
jeelizfacefilter
WebGL face detection and head-pose tracking from webcam video, for AR filters
- Stars
- 3k
- License
- Apache-2.0
- Last commit
- Nov 2025
- Last release
- Nov 2021
- Language
- JavaScript
2,881 on 21 Apr 20262,957 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
JavaScript library that runs a neural network in WebGL to detect and track faces in a WebRTC camera feed. It outputs raw data: detection state, face position and scale, rotation Euler angles, and mouth opening. It ships no 3D engine, with demos for THREE.js, Babylon.js, A-Frame, CSS3D, Canvas2D and Cesium.
Who it is for: Web developers building browser AR face filters or head-controlled interfaces
Strengths
- Framework-agnostic raw outputs: detection flag, position, scale, Euler angles
- Tracks multiple faces and supports several simultaneous video sources
- Many demos with source: face swap, glasses try-on, head-controlled cursor
- Alternate neural net files, e.g. NN_4EXPR_1.json for four expressions
Weaknesses
- Last tagged release is from 2021-11-12
- Outputs only pose and mouth opening, not dense facial landmarks
- Demos and repository content fall under a separate FaceFilter license note
- Some listed demos are marked as no longer maintained
What it needs
- Needs WebGL, WebRTC camera
- Models: NN_DEFAULT.json, NN_4EXPR_1.json
Quick answers
Is jeelizfacefilter open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |