Google’s New Program ‘AutoDraw’ Will Help Your Drawings Suck Less

http://interestingengineering.com/googles-new-program-autodraw-help-drawings-suck-less/

AutoDraw uses machine learning to match your doodles with professional works in order to clean up a sketch.

Simply pull up AutoDraw on your phone, tablet, or desktop computer and start sketching. 

As you draw, image suggestions will appear above the drawing pad. 

“We hope AutoDraw will help make drawing and creating a little more accessible and fun for everyone,” said the Google AI Experiments team.

I found this AutoDraw interesting and entertaining. Try it at

https://aiexperiments.withgoogle.com/autodraw

https://www.autodraw.com

3 Comments

  1. Tomi Engdahl says:

    New Google Project Lets You Collaborate On Doodles With A Neural Network
    https://tech.slashdot.org/story/17/07/01/047237/new-google-project-lets-you-collaborate-on-doodles-with-a-neural-network?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+Slashdot%2Fslashdot%2Fto+%28%28Title%29Slashdot+%28rdf%29%29

    Google Brain’s latest experiment is a neural network that allows you to collaboratively draw with it inside of your web browser in real-time. The neural network is trained using the drawings collected from an earlier web game called Quick, Draw! released a few months earlier.

    https://magenta.tensorflow.org/assets/sketch_rnn_demo/index.html

    Reply
  2. Tomi Engdahl says:

    Draw Together with a Neural Network
    https://magenta.tensorflow.org/sketch-rnn-demo

    What do 50 million drawings look like?
    https://quickdraw.withgoogle.com/data

    Reply
  3. Tomi Engdahl says:

    Microsoft’s new AI bot creates drawings based on text descriptions
    https://www.techworm.net/2018/01/microsofts-new-ai-bot-creates-drawings-based-text-descriptions.html

    Microsoft’s new AI tool draws beautiful images from text

    The Artificial Intelligence (AI) technology has incredibly evolved over the last few years and is touted to be the next big thing of the future.

    One machine learning model generates images from text descriptions, while the other model known as a discriminator uses descriptions of text to judge the authenticity of generated images, so that it cannot be tricked. Working together, the discriminator pushes the generator toward perfection.

    Reply

Leave a Reply to Tomi Engdahl Cancel reply

Your email address will not be published. Required fields are marked *

*

*