Making masks -- warning double nerd alert

ruttrutt Registered Users Posts: 6,511 Major grins
edited March 6, 2006 in Finishing School
Warning, this is only for the most serious kind of nerds.

Does anyone know this work: http://grail.cs.washington.edu/projects/digital-matting/image-matting/

I've seen the results in the paper and other results in a digital photography course I'm auditing at MIT. Amazingly good.

Now I want the thing. It solves what I consider to be the absolute most frustrating, time consuming problem in image post processing. I've been known to oursource. I've used Knockout. This technique could power a Knockout clone that would actually work.

Anyone want to whip up a Photoshop plugin overnight?
If not now, when?

Comments

  • jfriendjfriend Registered Users Posts: 8,097 Major grins
    edited March 6, 2006
    Count me in too!
    rutt wrote:
    Now I want the thing. It solves what I consider to be the absolute most frustrating, time consuming problem in image post processing. I've been known to oursource. I've used Knockout. This technique could power a Knockout clone that would actually work.

    Anyone want to whip up a Photoshop plugin overnight?
    If it's as good as it says and somebody integrated it into CS2, I'd buy it too.
    --John
    Homepage • Popular
    JFriend's javascript customizations • Secrets for getting fast answers on Dgrin
     Always include a link to your site when posting a question
  • DoctorItDoctorIt Administrators Posts: 11,951 moderator
    edited March 6, 2006
    So as Rutt described it to me, this is image processing done by super nerds in environments such as Matlab because "photoshop can't handle it". If anyone here figures out how to implement this, they will definitely be crowned uber nerd of dgrin!
    Erik
    moderator of: The Flea Market [ guidelines ]

  • BrettGBrettG Registered Users Posts: 120 Major grins
    edited March 6, 2006
    <snip from site>
    Addendum
    We forgot to mention one thing in the paper... We used eigen-analysis to find the orientation of the covariance matrix and added \sigmac2 in every axis. That is, we decomposed \SigmaF as U S VT. Let S=diag{s12,s22,s32}, we set S'=diag(s12+\sigmac2, s22+\sigmac2, s32+\sigmac2) and assign the new \Sigma_F as U S' VT. ...


    Oh well then... over sigmac2... well sure...

    :bash

    (I got nothin)
    BrettG
  • Mike LaneMike Lane Registered Users Posts: 7,106 Major grins
    edited March 6, 2006
    BrettG wrote:
    <snip from site>
    Addendum
    We forgot to mention one thing in the paper... We used eigen-analysis to find the orientation of the covariance matrix and added \sigmac2 in every axis. That is, we decomposed \SigmaF as U S VT. Let S=diag{s12,s22,s32}, we set S'=diag(s12+\sigmac2, s22+\sigmac2, s32+\sigmac2) and assign the new \Sigma_F as U S' VT. ...


    Oh well then... over sigmac2... well sure...

    OMG that's, like, so obvious <img src="https://us.v-cdn.net/6029383/emoji/Laughing.gif&quot; border="0" alt="" >Z!!!1!11!!!!

    Just the other day I was like d00d, we totally decomposed \SigmaF as U S VT. And d00d was like no duh, you used eigen-analysis to find the orientation o the covarience matrix and added \sigmac2 in every axis.

    Rad. c u l8r y0!
    Y'all don't want to hear me, you just want to dance.

    http://photos.mikelanestudios.com/
  • ruttrutt Registered Users Posts: 6,511 Major grins
    edited March 6, 2006
    If it was easy, everyone (err, someone) would have done it.
    If not now, when?
Sign In or Register to comment.