воскресенье, 5 апреля 2020 г.

Generate Facial Filters with #Shaderbooth #Facemesh and #tensorflow.js #MachineLearning @maxbittker

This filter gives a very “Dark Phoenix” vibe from shaderbooth.com

 

@maxbittker recently released Shaderbooth.com which allows users to write and play with new indie face filters using GLSL. @maxbittker posted about the impetus for the project on twitter saying that he hopes that the website, “helps people to code fun effects that they can share with their friends” and encourages indie development of creative filters.

The code for each filter is superimposed on the screen so you can live edit. Once you’ve developed a filter you like, you can submit it to be part of the preset filters. This was my first time working with GLSL and I found it pretty straightforward. Below you can see some examples of changing the default “blue mask” to green and orange.

Editing the code on Shaderbooth.com

Shadderbooth.com uses tensorflow.js and the Facemesh machine learning pipeline to identify facial landmarks for the filters.

MediaPipe Facemesh is a lightweight machine learning pipeline predicting 486 3D facial landmarks to infer the approximate surface geometry of a human face.

If you’d like to learn more, the code for the project can be found on GitHub. If you’re curious about some of the effects built by other users, check out what I’m calling the ‘cyclops’ filter below. If you’d like to play with other similar projects that inspired Shaderbooth, check out hydra and shadertoy.

I’m calling this the “cyclops” filter, built by @rickyreusser on Shadderbooth.com

 

Written by Rebecca Minich, Product Analyst, Data Science at Google. Opinions expressed are solely my own and do not express the views or opinions of my employer.


from Adafruit Industries – Makers, hackers, artists, designers and engineers! https://ift.tt/2UJyTgc
via IFTTT

Комментариев нет:

Отправить комментарий

Know us

Our Team

Tags

Video of the Day

Contact us

Имя

Электронная почта *

Сообщение *