×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Software Converts 2D Images To 3D

CmdrTaco posted more than 4 years ago | from the still-waiting-for-the-avi-to-3ds-converter dept.

Graphics 152

eldavojohn writes "Dr. David McKinnon from Queensland University of Technology, has recently launched a site that turns your sets of 2D images into 3D bump maps by way of 8 years of his research. The catch is that you need to have between five and fifteen photos of your object and they must overlap at least 80 to 90 percent. So with a video of an object, one might be able to extract every nth frame and use this site to generate a 3D model. Doctor McKinnon said, 'The full version of this software would be great for realistic learning simulators and training software, where you want everything to look like the real thing. This technology could also be great for museums wishing to turn their display objects into 3D images that can be viewed online. We are even looking into making 3D models of cows to save farmers spending thousands of dollars transporting their cattle vast distances to auction sites, allowing for an eBay style auction website for cattle. Films, animations and computer games could also benefit, since 3D film making is taking over from the traditional 2D method of filmmaking. Another application is allowing people to create 3D models of their own face to use on their avatar in computer games or 3D social networking sites such as Second Life or Sony's Home.' Physorg has more details."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

152 comments

VERY, VERY (0, Informative)

Anonymous Coward | more than 4 years ago | (#28637529)

old news.

Re:VERY, VERY (1, Interesting)

Beardo the Bearded (321478) | more than 4 years ago | (#28637717)

You know what, AC, you're right.

This guy has wasted his life. EMC2, an Ubuntu-based CNC milling program, has a JPG to G-code generator. A company I've worked for did this with some commercial success turning baby handprints and footprints into custom milled embossed plaques.

You take your picture, finesse it, and turn it into a 3D-object. Several CAD programs, such as Rhino and Solidworks, have plugins that do the same thing. There are dozens of programs that do this for various prices.

Even better, they only require ONE image.

Re:VERY, VERY (1)

jellomizer (103300) | more than 4 years ago | (#28637815)

Quite, He either wants geek cred points or is trying to get his PHD with this. If they know this is already out he could loose his grants

Re:VERY, VERY (0)

Anonymous Coward | more than 4 years ago | (#28637911)

This guy has wasted his life.

This is a public face on an interesting problem. Sure he gave you a dumbed down demo but surely he made some advances in computer vision in the process of making this demo.

When your robot can navigate any foreign environment or your Natal 2 can work without a time-of-flight sensor remember its because of the work on "Structure and Motion" by guys like this (and me).

OTOH, I won't argue with you if you think abstract research is a waste of time. I'll just ask you to turn in your nerd card.

MER does it [Re:VERY, VERY] (1)

Geoffrey.landis (926948) | more than 4 years ago | (#28638861)

When your robot can navigate any foreign environment or your Natal 2 can work without a time-of-flight sensor remember its because of the work on "Structure and Motion" by guys like this (and me).

The Mars Exploration Rovers convert stereo-pair photographs into 3-D terrain models every day, and have been doing this for five years. It's not at all clear what this guy is doing that's new, although I expect if I had the time to drill down through the popularizations to the actual technology, it would be clear.

Now, having a robot that understands what it's seeing, without human input, is much harder.

Re:VERY, VERY (4, Informative)

JoshuaZ (1134087) | more than 4 years ago | (#28637955)

It is impossible to in general extract a true 3D image from a single 2D image. There are ambiguous cases. In fact, there are even ambiguous cases for two images. When one uses CAD and such to make 3D out of 2D images one is making implicit choices (generally using heuristics about how the objects are likely shaped). One can however use multiple images from slightly different angles to extract a close to unambiguous result. However, doing that is not easy and that seems to be what they are doing here.

Re:VERY, VERY (1)

smellsofbikes (890263) | more than 4 years ago | (#28638873)

Case in point: Steinmetz Solids [wolfram.com], or mouhefanggai, that appear to be spherical from some angles, and hexagonal from other angles. Or the solid letters on the cover of the book Godel, Escher, Bach [wikipedia.org], that only make sense if viewed isometrically: a picture along any axis gives a completely different set of information than the other axes.

Re:VERY, VERY (0)

Anonymous Coward | more than 4 years ago | (#28638067)

Wait, which are those magical plugins that produce a good 3D model from a single image? I sure would like to see them.
The only technique i know to get a depth map from a single picture is shape from shading, and it has numerous issues (uncertainties due to unknown camera parameters and albedo).
I think you are just full of it.

Re:VERY, VERY (3, Insightful)

TerranFury (726743) | more than 4 years ago | (#28638071)

Even better, they only require ONE image.

In other words, it's not the same problem.

This guy has wasted his life.

Ouch. So if it's not a huge discovery in an entirely new research area, it's worthless? Would you be willing to apply this criterion to your own accomplishments?

Re:VERY, VERY (5, Funny)

Anonymous Coward | more than 4 years ago | (#28638173)

This guy has wasted his life. ... There are dozens of programs that do this for various prices. Even better, they only require ONE image.

Okay, smart-ass, here's your ONE image. [wikimedia.org]

Re:VERY, VERY (0)

Anonymous Coward | more than 4 years ago | (#28638877)

Wow, ok, I have seen that one on paper, but a photo of it, dang, that is impressive, did they manage to make a physical version that would look convincing, or is it all photoshop?

Re:VERY, VERY (2, Funny)

Hognoxious (631665) | more than 4 years ago | (#28639165)

It's quite possible to build one, but it only works from one angle.

If you were in the tree (where the girl's left arm is pointing) you'd see something like:

  /
\|

Re:VERY, VERY (2, Funny)

Inda (580031) | more than 4 years ago | (#28639999)

I have mod points but I just had to reply while the laugh is still fresh.

An ASCII picture of a Penrose triangle. Never thought I'd live to see the day. Well done Sir.

Dear Beardo The Weirdo: (0)

Anonymous Coward | more than 4 years ago | (#28638325)

Dear Beardo:

The initial VERY VERY is mine.

BTW, here's what Google Search returns for

2D to 3D Conversion [google.com].

Please change my initial comment to VERY, VERY, VERY old news.

Yours In Stereo,
Kilgore Trout

Re:VERY, VERY (1)

kestasjk (933987) | more than 4 years ago | (#28638343)

If it's supposed to extract 3D data from a single 2D image clearly there's a catch. Model tweaking required? Limited types of images that can be processed? Inaccurate? Suppose I took a photo of a photo, or there was a picture on a wall; how is it supposed to know what's 2D and what's 3D, or what depth things have? Shadow analysis can only go so far.

If this software works flawlessly but requires more pictures it's much more important than something theoretical/flawed. If you want a 3D model of something you have to expect to take more than one picture.

Re:VERY, VERY (0)

Anonymous Coward | more than 4 years ago | (#28639073)

Even better, they only require ONE image.

I don't know how to break this to you gently.

BullFUCKINGshit.

Re:VERY, VERY (1)

Khyber (864651) | more than 4 years ago | (#28639711)

"This guy has wasted his life."

Saith the foolish geek posting on Slashdot.

Pot, meet kettle.

Re:VERY, VERY (1)

tixxit (1107127) | more than 4 years ago | (#28639055)

Yes. This is actually a fairly common graduate (Masters) level project in computer vision courses. My version was even made for the web...

How much of the image is real? (2, Interesting)

Jurily (900488) | more than 4 years ago | (#28637541)

between five and fifteen photos of your object and they must overlap at least 80 to 90 percent.

So the 3D object in question will only have a front side? That's nowhere near enough for all sides.

Re:How much of the image is real? (3, Informative)

sys.stdout.write (1551563) | more than 4 years ago | (#28637591)

So the 3D object in question will only have a front side? That's nowhere near enough for all sides.

It creates a bump map, not a 3D model. Think of a brick wall in a video game. This is simply a texture image stamped on to a rectangle, but newer games use bump maps to make the bricks stick out. This generates that bump map for you.

Re:How much of the image is real? (0)

Anonymous Coward | more than 4 years ago | (#28638209)

A bump map is an implicit 3D model: Apply it as a displacement map to a flat surface, voila, 3D model.

Re:How much of the image is real? (1)

sys.stdout.write (1551563) | more than 4 years ago | (#28638869)

You are making the assumption that there are no concavities.

Try using a displacement map to do a face and you'll notice that the nostrils are totally fudged up.

Re:How much of the image is real? (0)

Anonymous Coward | more than 4 years ago | (#28639451)

Not every model can be losslessly converted into a bump map, but every bump map can be losslessly converted into a 3D model.

Re:How much of the image is real? (1)

MikeBabcock (65886) | more than 4 years ago | (#28639009)

A bump map is a height field, not a full 3D map. A bump map just describes heights of various places along the texture map, and never more.

Re:How much of the image is real? (2, Informative)

esampson (223745) | more than 4 years ago | (#28640169)

Actually it does create a 3D model. The summary is a bit misleading. I went straight to the website, hoping to get in before the slashdot, and examined some of the results. After the photos are processed a 3D model is built and the bump map is generated off of that. You can also download the model separately as a .ply file.

Re:How much of the image is real? (3, Interesting)

quadrox (1174915) | more than 4 years ago | (#28637619)

If you can generate this sort of bump map for each of the 6 sides (think a cube) you should be able to generate an actual mesh. At least you'll have the precise 3D location for each pixel, shouldn't be too difficult to create a mesh from that.

3D is a gimmick! (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#28637557)

Shamelessly stolen from Michael Kupperman [twitter.com] :"Classic 3-D films include "Comin' At Ya!", "Headin' For Ya!", and my favorite,"Look out- I'm Hurlin' Objects At Your Head!""

8 years for cattle modeling? (1)

noundi (1044080) | more than 4 years ago | (#28637629)

We are even looking into making 3D models of cows to save farmers spending thousands of dollars transporting their cattle vast distances to auction sites, allowing for an eBay style auction website for cattle.

-So... you spent the last 8 years of your life to develop a 3D generator so that one day you may help farmers model their cows instead of spending thousands(!!!) of dollars on transfering them for auction?
-Yes.
-OK, just checking.

Re:8 years for cattle modeling? (1)

RobertB-DC (622190) | more than 4 years ago | (#28638033)

Not to mention the fact that cattle buyers (like my former stepdad in Oklahoma) seldom if ever need to see a three-dimensional model of a cow before deciding whether to purchase it. They already KNOW what a cow looks like in three dimensions. A grainy video of cattle grazing in a field is more than enough -- and *that* technology has been around since the early 1980s (and has led to the demise of most small-town cattle auctions).

Anyone who proposes an "eBay for Cows" has never been involved in real-world cattle buying. It's like saying "I've got a great idea, I'll make 3D scans of stuff in my garage, and it'll be like 'eBay for Worthless Crap'!"

Re:8 years for cattle modeling? (1)

MonsterTrimble (1205334) | more than 4 years ago | (#28638927)

Agreed. It's not just about how a cow looks, it's how it moves. How someone looks & feels can be easily faked when doing photography - and I don't mean with photoshop. Ask any photographer and they will rattle off tricks to help you lose the extra chins, have thinner shoulders, hide certain things, etc. When you are looking at buying a cow you look at things like how alert it is, how it moves, etc. Hence why you can use a film when buying cattle. Alternatively (since 99.9% of slashdotters have no idea about the cattle industry) it's the same as buying a car. Pictures are fine, but they can't be substituted for driving it and feeling how it rides, weird noises and so forth.

Re:8 years for cattle modeling? (1)

Cryophallion (1129715) | more than 4 years ago | (#28638771)

Personally, I'm about thinking of launching a cow airbrushing service website.

Ummm... Oops. Whoever read that above sentence needs to sign an NDA.

Why bother (3, Funny)

MrMr (219533) | more than 4 years ago | (#28637647)

Cows are spherical, as every mathematician knows.

Re:Why bother (0)

Anonymous Coward | more than 4 years ago | (#28637667)

No. That's what a physicist knows. The mathematician doesn't know what you mean when you say cow, unless you also mention the field the cow comes from.

Only if it makes the math easier (1)

0100010001010011 (652467) | more than 4 years ago | (#28637709)

Favorite quote from my Mechanical Systems professor. I was surprised how much ME's use that in the real world.

Re:Why bother (1)

JiffyPop (318506) | more than 4 years ago | (#28637715)

Cows are spherical, as every mathematician knows.

And every physicist will tell you that a cow can be reasonably approximated as a point mass.

Re:Why bother (2, Insightful)

BlackPignouf (1017012) | more than 4 years ago | (#28637795)

Actually, they're toroidal, just like us.
That's one of the reasons why we couldn't live in a 2D world : our digestive tract would cut us in halves. :)

Cows are fractal . . . (4, Interesting)

PolygamousRanchKid (1290638) | more than 4 years ago | (#28637845)

Re:Cows are fractal . . . (1)

alexhard (778254) | more than 4 years ago | (#28637923)

It boggles the mind that someone would create something awesome like that and then not release it at desktop (or at least high) resolutions.

Re:Cows are fractal . . . (2, Informative)

chammy (1096007) | more than 4 years ago | (#28639347)

The script he used is linked at his site, just stick a cow model into blender and render to whatever resolution you would like.

Re:Why bother (3, Informative)

nick_davison (217681) | more than 4 years ago | (#28637885)

Any biologist will tell you: the digestive tract is external (there's never any form of membrane that has to be passed to get from one end to the other). I'd suggest that makes cows a torus.

Mmmm.... Having gone from cows' rectums to a torus, who's up for donuts this morning?

Re:Why bother (1)

Beardo the Bearded (321478) | more than 4 years ago | (#28638193)

Mmmm.... Having gone from cows' rectums to a torus, who's up for donuts this morning?

Many doughnuts are made with beef tallow, so you're not far off.

Re:Why bother (4, Funny)

DriedClexler (814907) | more than 4 years ago | (#28638077)

Every mathematician knows you can't get a 3D view from a 2D one. Like the old joke says ...

Three long-time friends meet up in Scotland. One is a biologist, one's a physicist, and one's a mathematician. As they're driving away from the airport into the Scottish countryside, they see a brown cow off in the distance.

The biologist says, "Wow, that's amazing! All the cows in Scotland are brown!"

The physicist replies, "No, all we really know is that some cows in Scotland are brown."

The mathematician replies, "No, all we really know is: there is at least one cow in Scotland, and this side is brown."

Thanks to you... (1, Funny)

Anonymous Coward | more than 4 years ago | (#28639661)

...I now know that Chocolate milk is imported from Scotland. Thanks for the enlightenment. :D

Re:Why bother (1)

UncleTogie (1004853) | more than 4 years ago | (#28639693)

The mathematician replies, "No, all we really know is: there is at least one cow in Scotland, and this side is brown."

I grok that we'll make a Fair Witness [wikipedia.org] of him yet!

FIRST PENIS!1 (-1, Troll)

clone53421 (1310749) | more than 4 years ago | (#28637659)

(Mods, please be kind. Somebody had to say it.)

Re:FIRST PENIS!1 (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#28637853)

Yeah, troll. I expected as much, but admit it... it's funny.

Re:FIRST PENIS!1 (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#28638417)

Somebody had to say it.

No, not really.

Re:FIRST PENIS!1 (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#28638603)

I thought it was hilarious.

Not normal maps? (1)

argent (18001) | more than 4 years ago | (#28637711)

Bump maps are so 20th century.

Re:Not normal maps? (0)

Anonymous Coward | more than 4 years ago | (#28638043)

Normal maps can be mathematically derived from bump maps (before runtime) so there is no problem here...

Stop living in buzzword world and get some practical competence...

That I need 15 photos is crap... other products like 3D Equalizer need only one photo where a mirror is held showing the same object from another perspective.. the 3D model (or surface) is then calculated from how specific points are shifted in the reflection..

Re:Not normal maps? (1)

tepples (727027) | more than 4 years ago | (#28639765)

If you have a height map, use its gradient [wikipedia.org] to compute the normal vector at each point on the surface. There's your normal map.

Re:Not normal maps? (1)

argent (18001) | more than 4 years ago | (#28640139)

If you have a height map, use its gradient to compute the normal vector at each point on the surface. There's your normal map.

That would seem somewhat akin to converting to a PNG from a JPG; the resulting normal map is less precise and of lower resolution than one you would derive from the original data.

Anyone care to explain (1, Interesting)

Anonymous Coward | more than 4 years ago | (#28637803)

Okay, so I'm not as dumb as this post will seem to make me by asking, but for the sake of the uninitiated...

What is a bump map? and how is it significant in relation to photos and 3D?

Misleading title (3, Interesting)

JobyOne (1578377) | more than 4 years ago | (#28637825)

Article title is misleading. A bump-map is less exciting than converting 2D to 3D. It's not like it's going to build a perfect model of your head from 15 photos.

Photosynth [photosynth.net] is far more interesting if you're excited by this concept.

Microsoft Synth (1)

cheetham (247087) | more than 4 years ago | (#28637871)

I assume this is a more fancy version of something like Microsoft PhotoSynth?

Shame it doesn't involve lasers. :-P

So, I know this is probably a well-researched area (1)

Merc248 (1026032) | more than 4 years ago | (#28637939)

But...

I've been doing some side research in computer vision for a month or two in order to solve a problem regarding constructing a fairly accurate 3D model of a cat walking in front of a webcam. I'm totally ignorant about the entire field, so I've been trading ideas with another friend of mine who actually brought up the idea in the first place. Some of the ideas went from some sort of "averaging" between rough 3D sketches of a cat between multiple frames (with some sort of checking to see if they are, indeed, "topologically equivalent" [within reason of course, we don't want cats to be equivalent to beach balls]) to simply checking for the cat by first getting the edges of all of the objects in the scene, and then checking out the shadows on the cat in order to check for features varying along the depth axis.

In any case, does anyone know of any good resources / articles that deal with this very problem?

Re:So, I know this is probably a well-researched a (1)

ColdWetDog (752185) | more than 4 years ago | (#28638185)

In any case, does anyone know of any good resources / articles that deal with this very problem?

Oh, this is simple. If it's moving and ignores you - it's likely to be a cat.

Bonus points if you can project laser dot and move it around. If the object tracts that, it's almost assuredly a cat.

Re:So, I know this is probably a well-researched a (1)

Merc248 (1026032) | more than 4 years ago | (#28638327)

Hahah, well, yeah. But what if there was a person who did the same exact thing? No, what if there was a person who did the same thing, AND he had a beach ball on top of his head with two ears pasted on top of it?

Mr Santax (4, Funny)

santax (1541065) | more than 4 years ago | (#28638005)

is uploading about 15000 pics of Halle Berry as we speak. Man I'm gonna have a blast tonight!

Umm.. maybe (2)

Lord Byron II (671689) | more than 4 years ago | (#28638045)

You take the cow to auction to sell it - to get it off your farm and on to someone else's. The point of the auction is to move the cow. It might be somewhat more efficient to move the cow directly from farmer to farmer, but this intermediate stop at an auction house can't be that big an inconvenience, can it?

It sounds like a solution in search of a problem.

Re:Umm.. maybe (1)

T Murphy (1054674) | more than 4 years ago | (#28638507)

I'm assuming once someone buys a cow at the auction house they are responsible for transporting the animal. If the same holds when the auction is online, the original farmer is no longer paying for transportation of the animals (if that is not the case, the buyer is no longer directly paying for transportation). You wouldn't buy a plane ticket from A to (random location), then (random location) to B- so why wouldn't you ship the cows directly? Not to mention at the auction site the cows have to be handled, fed, tracked and sorted; that is a lot of work (cost) that can be removed if the cows are kept on the farm until they can be shipped straight to the new owner.

Re:Umm.. maybe (1)

RemoWilliams84 (1348761) | more than 4 years ago | (#28638761)

You wouldn't buy a plane ticket from A to (random location), then (random location) to B-

You obviously don't fly much. Lay-overs suck.

Re:Umm.. maybe (1)

T Murphy (1054674) | more than 4 years ago | (#28639813)

That's what I said: you don't want to do that; if you can efficiently go straight from A to B you do so.

Re:Umm.. maybe (0)

Anonymous Coward | more than 4 years ago | (#28638683)

He was being prosaic, I believe. He chose the cow as an example so you would forget it much faster and come to the more voyeuristic natural usage by yourself. Before you got around to posting. "Being there", where "there" is not so much with a cow, but with some hot grits and ...

Re:Umm.. maybe (2, Insightful)

DragonWriter (970822) | more than 4 years ago | (#28639449)

It might be somewhat more efficient to move the cow directly from farmer to farmer, but this intermediate stop at an auction house can't be that big an inconvenience, can it?

Sure, it can (especially if the place the cattle end up going is closer to where they came from than the auction house is to either). Probably more importantly, so can actually having and supporting an auction house capable of holding cattle auctions (cattle are large, live animals), even before considering transportation. So that adds a substantial transaction cost to auctioning cattle. If you could do it online with equal confidence, that would reduce the transaction costs substantially.

Re:Umm.. maybe (1)

rm999 (775449) | more than 4 years ago | (#28640001)

"It sounds like a solution in search of a problem."

Welcome to the world of academia :)

What about videos? (0)

Anonymous Coward | more than 4 years ago | (#28638047)

Obviously since videos are just sequences of overlapping images, coupled with relatively rare scene changes, could this program be used to generate whole 3D models of videos?

These are Displacement Maps, not Bump Maps (0)

Anonymous Coward | more than 4 years ago | (#28638179)

A displacement map actually distorts the surface of your 3D object. A bump map simply creates the illusion of surface detail based on the angle of light relative to the geometry face normals. Anyone with a rudimentary knowledge of 3D modeling and rendering should know the difference between the two, so their use of this terminology is strange.

This is Crazybump (2, Interesting)

alteveer (979070) | more than 4 years ago | (#28638197)

...except Crazybump (http://www.crazybump.com/) is faster, funnier, and has more features. Indispensable for 3D shader development.

Re:This is Crazybump (1)

url00 (1345327) | more than 4 years ago | (#28640231)

...except Crazybump (http://www.crazybump.com/) is faster, funnier, and has more features. Indispensable for 3D shader development.

I wish I had mod points, I would give you a raise!

WRONG!!! (0)

Anonymous Coward | more than 4 years ago | (#28638201)

since 3D film making is taking over from the traditional 2D method of filmmaking.

This is absolutely... positively... WRONG!

They have this in DS9 (1)

Crock23A (1124275) | more than 4 years ago | (#28638271)

Quark tried to take 'images' of Major Kira so he could re-create her 3-D image in the holodeck for some pervy customer.

Re:They have this in DS9 (0)

Anonymous Coward | more than 4 years ago | (#28638455)

Since when is it pervy to want to have sex with an avatar who's source material was secretly generated without permission?

Hmm. I guess since 'always'.

Well played Crock23A. Well played.

Re:They have this in DS9 (3, Funny)

mistermocha (670194) | more than 4 years ago | (#28638513)

That's nothing! CSI Miami takes crappy security cam shots from hundreds of feet away to turn a speck that covers eight pixels into a full 3D model of the killer every week, and that's in THIS century and planet!

What about videos? (2, Interesting)

MindVirus (1424817) | more than 4 years ago | (#28638363)

What happens if we use this for videos (which are just sequences of generally overlapping images)?

If any progress could be made in this department, we could make video game maps by simply recording a factory with a video camera.

dating websites (1, Interesting)

Anonymous Coward | more than 4 years ago | (#28638365)

This would be very useful on dating websites where you need to know if the girl has a big ass. They often provide a very vague 2D image of their frontside.

New Gilligan's Island (1)

camperdave (969942) | more than 4 years ago | (#28638423)

This is Great! Now we can feed in old episodes of Gilligan's Island, extract 3D facial maps of each of the castaways, and paste them onto different actors. Finally we can produce new episodes! We can replace Fake Ginger with Real Ginger in the movie. Imagine the possibilities!

Now, if only voice reproduction and voice morphing technology was moving at the same pace as video.

Re:New Gilligan's Island (1)

Maximum Prophet (716608) | more than 4 years ago | (#28638969)

Now, if only voice reproduction and voice morphing technology was moving at the same pace as video.

I've always wondered about that. Sound recording is so much easier than video, you'd think that bringing a dead actor's voice back to life would be a piece of cake compared to their image, but it's not. I guess that's just and example of some things that are a lot harder than they seem at first. (Like predicting the weather)

Re:New Gilligan's Island (1)

camperdave (969942) | more than 4 years ago | (#28639383)

Perhaps it's a lot easier to fool the eye than to fool the ear. My guess is that there just isn't as much demand for high resolution, digitally generated sound as there is for video, so fewer people are really working on it.

Getting closer... (1)

bill_kress (99356) | more than 4 years ago | (#28638429)

I've always thought it would be cool to have a tool that could take scenes from old movies where the camera was pointing out the window of a car and convert it into a perfect 3-d map.

You could even extract the people and build models from them including movement.

It's kind of the same as when they put all those dots/lines on a person's body to be able to model the exact movements of the body, just using smarter software instead of dots...

You could gather massive amounts of data from a single shot once a computer can fully comprehend what's going on in the shot.

porn??? (0)

Anonymous Coward | more than 4 years ago | (#28638715)

Why is "porn" in the tags?

I've been in the field for years (0)

Anonymous Coward | more than 4 years ago | (#28638743)

'Cause those cow pics aren't always too flattering. So someone needs to clean them up to put her from her best side.

So the boss will say "Those udders aren't big enough. I want big udders. Frickin' huge. And they should be bright pink. Get rid of all the veins and stuff". And I'll just give the udders a bit of a polish, make her a bit more toned, sort out any spots or skin problems. If the guy wants to meet her, it's not like it's not the same cow, maybe she just has a bad hair day.

Nothing new... (0)

Anonymous Coward | more than 4 years ago | (#28639025)

This is how 3-d terrain mapping has been done for almost two decades.

Overlapping photographs (from a plane) are scanned and then processed by software that computes parallax for thousands of points across the overlapping images to compute depth changes.

Not impressed (1)

godrik (1287354) | more than 4 years ago | (#28639147)

what's new here ? Three dimensional reconstruction from images or video are not really new. The INRIA does it for a long time ( http://grimage.inrialpes.fr/index.php [inrialpes.fr] ) and even forked a startup that works with the cinema industry ( http://www.4dviews.com/ [4dviews.com] ). I even recall a demo which is two or three years old where a guy playd street fighter in front of several cameras. I was not able to RTFA (slashdotted), so can someone enlighten me ? Is the novelty the webservice ?

How many time (1)

werfu (1487909) | more than 4 years ago | (#28639255)

before someone comes up with stereoscopic porn?

Re:How many time (1)

gurps_npc (621217) | more than 4 years ago | (#28640123)

Uhm, I hate to tell you but porn was some of the FIRST things they made into steroscopic images. Just go looking for it and you will find it. Much of it uses the red-green 3d glasses to view.

Do the Shroud dude! (2, Funny)

tjstork (137384) | more than 4 years ago | (#28639733)

If you are really going to try and take your technology mainstream, you may as well go and get a bunch of Shroud of Turin pictures, use your technology to reconstruct Jesus in 3d, and get yourself a guest TV spot on Fox. If your Jesus winds up looking like Peter O'Toole, so much the better!

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...