Blog Post

TechFest 2011: ShadowDraw

Download this episode

Download Video


Do you want to be able to sketch or draw better? ShadowDraw is an interactive assistant for freehand drawing. It automatically recognizes want you’re trying to draw and suggests new pen strokes for you to trace. As you draw new strokes, ShadowDraw refines its models in real time and provides new suggestions. ShadowDraw contains a large database of images with objects that a user might want to draw. The edges from any images that match the user’s current drawing are merged and shown as suggested “shadow strokes.” The user then can trace these strokes to improve the drawing.

Click here for some more in depth info and RIN (Rich Interactive Narrative)




Available formats for this video:

Actual format may change based on video formats available and browser capability.

    The Discussion

    • User profile image

      They need to have all the drawings from FurAffinity. I am a big fan of it.

    • User profile image
      Andreas Balzer

      Where's the "download alpha version" link? ;)

    • User profile image
      Mr Crash
      @Laura Foy:
      When you talk into the mic it gets really loud (hurts my ears), can you please think of that next time.
      I'm guessing you don't know how to use a mic correctly, please read up on it.
      Examples; distance mic to mouth, how you hold the mic (ex talk over the mic Not into it)

      Mine and others ears will thank you.

      (When others talk, their voice is normal but when you talk it's like you scream into the mic.)
    • User profile image

      Pretty cool stuff. Lines up nicely with Gustav.

    • User profile image

      @Mr Crash: That is because I am from New York and I am LOUD...and I interview soft spoken developers Smiley

    • User profile image

      I've got to agree with Mr Crash here. Some points of this video are ear blowingly loud.
      "one generic BICYCLE"
      As for the technology, very cool. It does have the issue where the more items you enable it to draw, the better you have to draw in the first place for it to be able to recognise what you are drawing. It seems to work well for the 30k images the system has now, will it still work as well for 10x that many?

    Comments closed

    Comments have been closed since this content was published more than 30 days ago, but if you'd like to send us feedback you can Contact Us.