This is really cool, but im not sure - how is it supposed to be used in games? Reality cant possibly be a better playground than specifically tailored VR.
I always saw AR as a convenient way to provide additional data on surroundings. Point out landmarks using a HUD in a car. A nice way to present information on a product (like an artificial "the company making this product supports SOPA" sticker :) ).
But I am really at a loss as to how this would be used in games. Virtual Pets maybe? but whats the fun of having to look at it through a 4 inch screen ? Hell, even his dancing foxes (or whatever they are) dont fit in tht ipad screen. The user sees the space right next to the ipad window, where they should be. And there's nothing there. Thats a huge immersion killer to me. Its not the same as with VR, as VR doesnt have to pretend the illusion is actually right behind the screen window. AR with full goggles ought to make up for that - but the hardware isnt nearly there yet.
This is technologically very impressive - but what can we really make of it?
I dunno. I forsee a pokemon game with creatures you have to look for to find, that can be accurately hiding behind/near/in things at various times of the day.
I can imagine several possibilities. Maybe something multiplayer using real terrain, like a scavenger hunt--you could mark objects and leave clues with this sort of tool. In fact, any sort of game that involves actually moving around could benefit from this, and I think games like that could be very interesting.
Another thought is board/card games (like Magic: The Gathering) could benefit from this. You could get nice little animation when you play your cards--not terribly useful, but could be very amusing. You could also have wizard chess like Harry Potter (sort of).
Really, the big trick is being able to integrate with the outside world. So this won't be great for entirely virtual games, but could be used as a "hook" into physical games.
Now implement a raytracer that infers lighting location and reflectance (and subsurface scattering) of the objects in the scene from the image and then we can have a whole new level of realism.
In all seriousness, though, I do wonder what kind of processing power you would need in a handheld device to be able to do that. Could we realistically achieve it within 15-20 years? It's certainly one of those "gimmicks" with extreme potential.
That little tangent about realism aside, the engine itself does look quite remarkable in how smooth it is able to run. I wonder hwo well it handles occlusion, changes in lighting and the other benchmarks for computer vision, as it was not demonstrated at all in the video. In fact, the presenter quite handily avoided putting his hand between the camera and the soda can.
Other than that, I can't say much without trying the thing, but I do not own an iOS device and don't plan to in the near future. If someone decides to try out the framework, I'd be glad to read a more detailed analysis of it.
Fully detecting a scene's lighting is a complex problem. This paper from last year was quite interesting: "Rendering Synthetic Objects into Legacy Photographs" - http://kevinkarsch.com/publications/sa11.html
This combined with existing techniques of constructing 3D geometry out of videos could work really well if say you wish to construct a game level out of a real scene.
Raytracing complex scenes on a hand-held device at interactive frame rates is still quite a bit off. But techniques where a lot of the calculations can be done offline are possible to use today (radiosity, etc).
As Geee stated, it's about imitating the lighting of the scene. There's all sorts of subtle and not-so-subtle effects that come as a result of light bouncing around.
While it may be obvious when a virtual object is missing a shadow (as in the demonstration video), even implementing that would not be enough to fool the human brain completely, though it isn't always obvious what the problem is, only a subconscious nagging.
If you're interested in what precisely the effects that the real world has and augmented reality generally doesn't have - i'd say the biggest ones are shadows (including soft shadows [0]), depth of field [1], ambient occlusion [2], and indirect lighting.
You don't necessarily have to write a full-blown raytracer with global illuminasion, casting billions of rays to get a passable result. All of the above mentioned things can more or less be approximated in some way, and most modern game engines do so (I don't know of any phone games that do, mind, as the calculations are still non-trivial, but I do remember an interesting tech demo from Nvidia).
The biggest problem, though, is that we can do these things in a controlled setting, where you know the exact shape, texture and light reflective properties on every object in the scene. As you can imagine, that is not so in the case of augmented reality (as I quipped in my earlier post, you would have to infer surface reflectance from the image in some way). Compared to the problem of global illumination in a virtual scene - well, let's just say it's orders of magnitude harder. I don't recall anyone actually having scanned a scene with a single camera. And that's an AI breakthrough that indeed people would talk about.
You would be able recreate the lighting conditions of the scene. This is the bottleneck of every AR application that aims for realism. Basically, you'll have to recreate every light source, every object, surface and volumetric properties of all objects to render completely realistic 3D objects in the scene.
Feature tracking on an object which stands out clearly against the background? Using morphing filters on the segmented object? Not that innovative.
Now I do like the particle trick. You see this in some video games to highlight objects of interest (e.g. World of Warcraft). It makes it much easier for players to locate them and zero in on them against background clutter. Probably useful for AR if you have a good application case.
However, the potential is heavily constrained until you get displays capable of "non-interfering annotation" - which is to say, you need a good HMD and not a phone. Not that you can go out and buy "a good HMD" by this measure, but that's a big thorny mess out to the side of the software concerns.
Games? Imagine Google giving away augmented reality glasses (let's call them Googgles) that help you find your way in the environment by allowing you to do a local search ('where are my car keys?'), by adding name tags to people you have seen before but do not know well, etc.
Now, that giving away comes at a price. Frequently, when a Dr. Pepper can enters your visual field, that can becomes an animated advert. Your glasses will know how to time those adverts so that they stay (just) below the nuisance point, because they will have read your gmail and that of your friends, and will know what you ate.
I always saw AR as a convenient way to provide additional data on surroundings. Point out landmarks using a HUD in a car. A nice way to present information on a product (like an artificial "the company making this product supports SOPA" sticker :) ).
But I am really at a loss as to how this would be used in games. Virtual Pets maybe? but whats the fun of having to look at it through a 4 inch screen ? Hell, even his dancing foxes (or whatever they are) dont fit in tht ipad screen. The user sees the space right next to the ipad window, where they should be. And there's nothing there. Thats a huge immersion killer to me. Its not the same as with VR, as VR doesnt have to pretend the illusion is actually right behind the screen window. AR with full goggles ought to make up for that - but the hardware isnt nearly there yet.
This is technologically very impressive - but what can we really make of it?