The CTO's word

Book: Deep Learning in the Browser

I have written a book about deep learning in the web browser. It is available on Amazon here. I wrote it with 3 co-authors, Kai Sasaki Christoph Körner, Reiichiro Nakano. It focuses on client-side deep learning implementations using JavaScript and WebGL. It deals both with using mainstream deep learning frameworks like TensorFlow.js and building deep neural networks from scratch with vanilla JavaScript/WebGL. The Github repository of the book is available here: All sample codes Read more…

Use cases

Jeeliz for embedded systems

At a first glance, it may seems strange to use Jeeliz technology for embedded systems. Indeed, its favorite environment is the web browser. But web programming seeps everywhere: in mobile applications with PWA (Progressive Web Apps), in desktop applications with Electron, server-side with Node.js, and even in blockchain based decentralized applications with Lisk for example. So why embedded systems? In this article we describe the main advantages of our technology compared to the use of Read more…

Use cases

Jeeliz for augmented reality

ARCore and ARKit The augmented reality frameworks ARCore and ARKit, released respectively by Google and Apple, have popularized the use of augmented reality. They rely on the computing power and the 3D scanning capabilities of latest high end mobile devices to provide a smooth experience. The main technological breakthrough is their SLAM (Simultaneous Localization and Mapping) algorithms which reconstructs the 3D environment and concomitantly computes the position and orientation of the device. They prepare the Read more…


Visit us at Paris Airport Startup Day

We will participate in the Paris Aéroport Startup Day. It will happen on October the 17th of 2018 in Paris Orly airport. All the informations are available on the official website of the event: On this occasion, we will show the JeelizBox working into a large JCDecaux 70 inches full HD advertisement display. The JeelizBox is so small that it can be embedded into an advertisement display, it’s a plug-and-play solution, and allows augmented-reality Read more…


Tutorial: Matrix theme JavaScript webcam face filter

In this tutorial you will learn how to build this webcam face filter : You can try it yourself by clicking here! Introduction Some native mobile applications such Snapchat, Facebook Lenses or MSQRD have popularized webcam face filters. There are even creative studio softwares to easily create face filters without requiring special computer development knowledge. It’s still time for you to take the blue pill proposed by Morpheus by launching Facebook AR Studio and stopping Read more…


New York City ARKit meetup, July 31th 2018

We explain the advantages of Jeeliz technology in this lightening talk, followed by a question session. Various demonstrations will be shown: face detection and tracking, expression detection, sunglasses virtual tryon and pupillometry. Our long term goals in augmented reality object recognition were also mentioned. The page of Meetup event is here: We will come back at another NYC ARKit meetups because they are simply awesome! The page of the Meetup group is here:

The CTO's word

Why WebML and Face Detection API will be rejected

Web programming is getting closer and closer to native programming. This is due to the performance increase of JavaScript engines and to the new functionalities brought by new APIs. There are among others : WebSockets for real time data transfer, MediaStream API to get the webcam video stream and to send it in peer to peer, WebGL to use the GPU for rendering or computing, WebAudio to use advanced audio features. Web programming has many Read more…


Meet us at the Creative Coding #8, NYC, May 23rd 2018

In this talk, we will explain how to get started to build your own JavaScript face filter. We present an interactive tutorial on WebGL Academy to understand step by step the different aspect of the final program (getting the webcam video feed, create the 3D scene, importing the 3D meshes, color harmonization…) The slideshow of the talk is available here: The tutorial about building a Statue of Liberty face filter is available on WebGL Read more…


Creating a Snapchat-like filter with Jeeliz’s FaceFilter API: Part 2, user interactions and particles

The FaceFilter API allows you to effortlessly create Snapchat-like filters in your web-apps. Built on our face detection neural network, it combines the power of deep learning with the versatility of WebGL/Three.js. Recap for the previous part: In the first part of this series, we first saw how to export a 3D model to JSON with Blender. We then added our hat to our Three.js scene, and thus became a true pirate of the Grand Read more…