http://www.extremetech.com/article2/0,2 … 811,00.asp
Thought this might be interesting to some.
Offline
Saint Paul, MN
Oh cool. My girlfriend will appreciate this, as she is a pixel artist.
Offline
Tokyo, Japan
Sweet mate! thanks for sharing. Be good if you could try your own though. I wonder what the Blip Festival or Dot_AY's website would look like depixelized!
Offline
Toronto, Ontario, Canada
Now we just need to find a way to go the other way. Make good looking pixel art from a high res image. Imagine how cool that would be.
Offline
Sweeeeeeden
Seems like he got slashdotted. His page barely responds...
Shame, I would've wanted to read the paper...
Edit: Found a link in the cmments to the article. http://www.mediafire.com/?1yagc72uz7lx8u2
Offline
Los Angeles, CA
This is really impressive. It's a shame they didn't put out the source, but then again MSR rarely does for patent-related reasons.
Offline
Venezuela
call me troll, purist, hater or whatever... but... is a shame that some ppl just relate pixelart to "8-bits video games" and they always use popular Video Games memes in the easy way. No creative or intellectual appreciation on the pixel art itself...
i would love to see somebody getting this popularity with his own art. Just ask to myself... why the easy way? why use popular memes?, im sure nobody will ever notice/public this if art was from any other artist
And yes, they arent pixel artists... but im just saying 
Offline
Minneapolis
ui- while I agree with your sentiment that pixel are *should* be valued as a medium in itself, it's clear that the public does not. Hence journalists do what they always do- dress the issue for public consumption. People know about videogames, kinda, but that's even a stretch for the average schmoe. Oh well. 
Offline
buffalo, NY
pointillism is original gangster pixel art.
http://en.wikipedia.org/wiki/Pointillism
Offline
Skimming over the intro to their research paper, there doesn't seem to be any reasons stated for why the hell any one would ever need an algorithm that can turn pixel art into, uh, "not pixel art." If any one can come up with some sort of practical reason for this, feel free to type half of it out, realize that it makes no sense, and then hold backspace for a second or two.
EDIT: Okay, maybe I'm overplaying it a little bit, but seriously, there's no point besides "it's possible I guess."
Last edited by Andrew Winzenburg (May 26, 2011 9:41 am)
Offline
Sweeeeeeden
ui: These guys are mathematical researchers. Their job is not to showcase pixel artists, but to showcase their algorithm. And for that reason I think it's actually the right choice for them to choose game sprites. The game sprites are neutral. Game sprites should be well polished, but don't really mean anything outside of the game context, which means the average reader will focus on what the algorithm does. More artistic artwork will likely beg the questions, where is this from, what does it mean? and take away the attention of the thing on display (the algorithm.)
And to continue the neutrality argument, game sprites are pixelated because they needed to be, and were actually usually not even perceived as being pixelated because of the TV screen's blur. It was never part of the aesthetic. Pixel art on the other hand, especially in recent years, is focusing on the pixelation as an aesthetic. It might even be seen as a light insult to the artist to depixelate their art. All of a sudden you have two conscious aesthetic choices that are competing, pixelated or depixelated, and the reader will perhaps not be judging the algorithm just on its technical merits because he may have a bias towards the pixelated aesthetic, if they were using "modern" pixel art as examples.
Offline
Sweeeeeeden
Andrew: If the algorithm would ever become fast enough for realtime use, I think it would be pretty cool for SNES games, in particular.
Offline
Tokyo, Japan
If you take the "pixel art" element out of the title and replace it with "vintage game sprites" then yes, as nitro has said directly above me: it is pretty cool. Why? cos you get to see you old favourite charcters in a totally different style.
Of course, doing this stuff to depixelate somthing that is supposed to be pixelated doesn't make any sense and (as stated) could be considered insulting to the artist(s)
Offline
hardcore, Australia
Andrew Winzenburg wrote:
Skimming over the intro to their research paper, there doesn't seem to be any reasons stated for why the hell any one would ever need an algorithm that can turn pixel art into, uh, "not pixel art." If any one can come up with some sort of practical reason for this, feel free to type half of it out, realize that it makes no sense, and then hold backspace for a second or two.
EDIT: Okay, maybe I'm overplaying it a little bit, but seriously, there's no point besides "it's possible I guess."
It would actually be very useful for upscaling small images.
It's more advanced than current algorithms in that it's making important decisions about straight lines, curves, shading differences.
If you want to upsize that 200x200 jpg you have, to say 800x800, it's going to look pretty shit, depending on which algorithm you use, (photoshop has bicubic and nearest neighbour, maybe more?) these are somewhat basic ways of upscaling, by either creating a square or many pixels to represent the one, or by shifting colours of pixels between the two original pixels.
This method seems to have some intelligence in deciding where to put a straight line, where things should be shaded or just a sharp colour change.
Offline
Sweden
Andrew Winzenburg wrote:
Skimming over the intro to their research paper, there doesn't seem to be any reasons stated for why the hell any one would ever need an algorithm that can turn pixel art into, uh, "not pixel art.
Try reading the "previous work" section. It lists previous research and applications of upscaling and vectorizing algorithms, fields where the work is highly relevant. You should also try reading the conclusions. Please, at least skim over the whole paper before assuming that the research is useless.