Keith Devens .com

In this paper we present a simple colorization method that requires neither precise image segmentation, nor accurate region tracking. Our method is based on a simple premise: neighboring pixels in space-time that have similar intensities should have similar colors... We demonstrate that high quality colorizations of stills and movie clips may be obtained from a relatively modest amount of user input.

Pretty incredible results. Via Wes

Permalink | 2 Comments | Tags: linkblog, Programming | id 6690

18:42 (utc-5)

Comments

M. Bean wrote:

I saw that a few days ago, and I think those results are dummied up.

They allow you to get a hold of the matlab scripts, and I ran some, as did some other people on a forum I frequent, and the results are extremely spotty and never look like that.

I'm not saying their approach isn't possible... it seems like it would be, but I don't think it's honed enough yet to produce the results they are showing on their page.

∴ M. Bean | 13-Mar-2005 10:28pm est | #7206

I'm highly doubtful as well.

∴ Keith | 13-Mar-2005 10:33pm est | http://keithdevens.com/ | #7208

Feel free to post a comment below. Please see my comment policy.

Formatting Rules (No HTML):

**bold**, *italic*, _underlined_, --strikeout--
"text"="url" creates a link, and URLs are auto-highlighted
Blockquote: Like e-mail, begin paragraph with > (greater-than sign)
Lists: begin paragraph with *,-, or + (unordered), or # (ordered)
Code block: ?!code:language=perl|php|sql|javascript|etc.{\n}...{\n}?!/code

RSS feed RSS feed for Keith's Weblog
Atom feed Atom feed for Keith's Weblog
Weblog archive
Recent comments
on 2 posts

Sunday, March 13, 2005

Image and movie colorization using optimization

Comments

Recent comments