Slashdot Mirror

The thing is that all that stuff is hard to use. You still need skilled people to get good results.

This is still true, but not for long. Erasing objects is easy with photoshop content aware fill. Adding objects will be easy soon:
Rendering Synthetic Objects into Legacy

Removing objects from images and filling in the missing space with some other content from the rest of the image based on 'awareness' has been available for some time now, it is called 'content awareness' in Photoshop and 'Resynth' in Gimp.

I had the same thought. Photoshop 7.0 (runs great through wine) fulfills all my photo-editing needs. I did pull up a changelog for a recent version of Photoshop, and it *does* appear to have some nice new features, but probably not worth the price for most people.

No, they haven't "developed a surveillance system". The paper is two psychologists blithering about the potential architecture of one. It reminds me of the awful papers that came from the "expert systems" community in the 1980s. There's been some progress; it mentions Bayesian statistics. But it's fundamentally an approach based on parsing visual data into something that looks like predicate calculus and grinding on that. There's a long history of that not working.

It's an idea in the right direction, though. A key component of intelligence is prediction. Knowing what is likely to happen is a basic component of common sense, an area in which AI systems have historically been weak. With prediction comes the ability to ask "what if" questions, essential to deciding what to do next without doing something stupid.

There's been real progress in that area, but not from the expert systems people. Adobe Photoshop's content-aware fill is an example of a successful system which has a form of "common sense" - it fills in plausible-looking areas to replace sections deleted from photos. Related technologies exist for videos, and are used for motion compression and 2D to fake 3D conversion. Systems which look at video and guess "what happens next" may be the next step.

Maybe you eyes don't feel strained when you look at blurry 2d stuff, but mine do.

Examples:
http://www.photoshopessentials.com/images/type/effects/light-burst/blurred-text.jpg
http://1.bp.blogspot.com/__e75oHvC5rk/SQB11qe8d_I/AAAAAAAAAIM/DRtUohJMzrA/s400/First+Try+Ss.jpg

And the rest of my points are still valid even if you don't read or understand them.

The "blur"/out-of-focus effect is not specific or even required in a 3D movie. You can have everything perfectly in focus in a 3D movie.

Well, it's flamebait, but not a troll.

As the referenced article points out, it really does make a difference when you start doing manipulations / editing to the photo. think about it. With only 8 bits, you have very little dynamic range, so expanding and contracting part of the range (as you do when you manipulate color) will cause serious artifacts. 16 bits means that the manipulations do not cause significant artifacts.

HOLY SHIT, you are fucking retarded.

http://www.photoshopessentials.com/essentials/16-bit/

Please, read this so you don't make a fool of yourself in the future.

In photoshop 8-bit = 16.8 million colors
16-bit = 281 trillion colors

As a supplement to your comment, here is the very next page of the link you posted:

Link

Yeah...16 bit color makes a HUUUUUGE and TOTALLY NOTICEABLE difference.

Now if only the open source community could come up with a Solution to this HUGE problem.

By the way - as a supplement to the comment above, here is a simple example of the difference between 8 bit and 16 bit colour: