Colorizing Images and Video by Scribbling

Guspaz writes "Up until now, colorizing a video or image has been a painstaking and mostly manual task. However, researchers in Israel have come up with a new way of colorizing images just by making a few scribbles. The technique works on the premise that 'neighboring pixels in space-time that have similar intensities should have similar colors,' and also allows colorization of videos by 'marking' about one in ten frames."

Mirror of the site, with images

[hankwang]

This page is over 10 MB, so it's electable as the fasted slashdotted site ever.

Here is the coralized mirror [nyud.net].

google cache

[dirvish]

http://66.102.7.104/search?q=cache:xOH_jKTvBeEJ:ww w.cs.huji.ac.il/~yweiss/Colorization/+&hl=en [66.102.7.104]

Re:A play on history

[srmalloy]

The problem with doing this is that, for any given camera, there will be a band of RGB color combinations that produce the same luminosity, so a single camera does not provide enough information to produce a full-color image. It requires several cameras, each filtered to a different spectral range, to be able to produce a full-color image, unless you know in advance that your image is monochrome.

Re:Let me be the first to say...

[sahonen]

Intensity actually takes most of the bandwidth of an MPEG stream, because human eyesight tends to notice changes in luminance more than changes in chroma. The chroma channels are compressed *extremely* heavily compared to the luma channel, and are actually even at a lower resolution.

Re:Let me be the first to say...

[Anonymous Coward]

Except that groupings of 4 pixels is not necessarily a good approach. For one thing, it may be far more color information than is really necessary. Besides that, two adjacent pixels may have significantly different colors. Carefully designed "scribbles" of color could very well take up less space and give better quality.

I'm sure there are good reasons for the JPEG/MPEG method, and I'd be a bit surprised if the groups in question didn't think of this possibility, but I still think it should theoretically give better results (at the cost of higher complexity and computational requirements).

Re:Let me be the first to say...

[s0me1tm]

24 bits per pixel X 4 pixels = 72 bits

In other news, mathematicians still agree that 24 times 4 is 96.

YUV 4:2:0 saves 50% bits over YUV 4:4:4, more info on wikipedia (per usual) http://en.wikipedia.org/wiki/Chroma_subsampling [wikipedia.org]

Re:Thank you.

[Evanisincontrol]

New equation:

Replying to yourself = +11 mod points

Interesting. Mods are funny people, I love'em. Such unpredictable little things, aren't they?

Re:Unfuckingbelievable.

[beetlefeet]

You get a much broader range of contrast when it's filmed on B&W film than a color image which has been desaturated.

A colour image is desaturated compared to a B&W image? Hello McFly?

Please look up saturation in regard to colour.

Hint: Try raising the saturation of a colour image in photoshop or gimp (ctrl-u in photoshop). Observe. Then try using the "Desaturate" function and see what you get.