search

jeeliz / jeelizFaceFilter

Javascript/WebGL lightweight face tracking library designed for augmented reality webcam filters. Features : multiple faces detection, rotation, mouth opening. Various integration examples are provided (Three.js, Babylon.js, FaceSwap, Canvas2D, CSS3D...).
https://jeeliz.com
Apache License 2.0
2.71k stars 535 forks source link

How to run jeeliz on a static image or custom video stream? #26

Closed qyikmk closed 6 years ago

qyikmk commented 6 years ago

I noticed that using JEEFACEFILTER.init() only allows for detection of the face on the video stream accessed through getUserMedia(). As far as I understand there is no way to control the image/video which jeeliz analyses. I found out however that your sunglasses example allows to upload a custom picture.

Is it possible to input custom image/video stream to jeelizFaceFilter ? If yes then how can I do it ? I've looked through the readme and tutorials but with no luck :(

xavierjs commented 6 years ago

This is possible: https://jeeliz.com/demos/faceFilter/demos/canvas2D/fromVideoFile/ and the source code: https://github.com/jeeliz/jeelizFaceFilter/blob/master/demos/canvas2D/fromVideoFile

qyikmk commented 6 years ago

Thanks!

tarasprystavskyj commented 5 years ago

This link is not working any more https://jeeliz.com/sunglasses/?sku=rayban_new_wayfarer_havane_marron_clair_degrade as this server is not accessible https://fallbackglassesdb.jeeliz.com/

Is there any other accessible link with this example of using an image as a source intead of a webcam?

xavierjs commented 5 years ago

Hi,

There was a problem with the image rendering server. I have restarted it and corrected some issue I noticed on the trunk 1 week ago. Thank you for you report.

Best, Xavier

tarasprystavskyj commented 5 years ago

Thank you for the quick turnaround. Where I can read about licensing of the module?

xavierjs commented 5 years ago

Hi,

Licensing of FaceFilter (this repo) is free since it is released under Apache2 licence.

However we provide developement services (integration/neural network improvement/specifics needs) using our libraries ( https://github.com/jeeliz ) to fit specific needs.

The glasses virtual tryon module used in https://jeeliz.com/sunglasses or https://github.com/jeeliz/jeelizGlassesVTOWidget is a specific case, because for this we provide the whole solution (hosting, glasses modelization, server side fallback rendering).