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."
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.
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.
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.
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.
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
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?
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."
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.
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?
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,
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
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.
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)
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.
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 comp
I'm posting this really late in the thread so maybe nobody will read it (or care) but... If there is one place on earth that is crying out to see this technology used it is the KILOMETERS (really!) worth of intricate stone carvings at Angkor Wat (Cambodia). I've thought about borrowing (stealing?) a friend's $500,000 laser scanner to capture them but the 1) he (his institute really) probably wouldn't let me 2) the thugs who run Cambodia would probably not let me use it without me paying some extortionate amount. There really is no-where else on earth where you can see the results of thousands of man-years of skilled stone carvers. This priceless cultural heritage should be captured before pollutants like acid rain slowly erodes it or thieves literally dynamite it to pieces. Now perhaps anyone with a good video camera, a steady hand, and a LOT of patience can get this done! Perhaps if this job is too large for any one individual to complete it could be done in sections and the individual video sequences shared over the internet. Anyway, I hope this software is modified to handle video (subject to certain restrictions such as shooting in progressive mode).
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.
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.
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?
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 y
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.
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!
Bump mapping [wikipedia.org] is often used to add textures to otherwise flat surfaces. Basically, the bump map is a channel where the intensity of a pixel represents the height (rather than colour) of the pixel.
It's very similar to this toy [shinyshack.com], which I'm sure you've probably seen before. The bump map represents the 3D shape of the object being portrayed. (It does have certain limitations; since each pixel can only have one height, the bump map can't represent surfaces which fold over themselves... e.g. a bump map of your face would look like your face from the angle it was intended to be viewed from, but from other angles you'd notice that the nostrils were solid underneath.)
Once you've generated a bump map, you can use it to render a true 3D surface, calculating the shadows based on the bump map and the position of the light source.
How much of the image is real? (Score:3, Interesting)
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? (Score:4, Informative)
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.
Parent
Re: (Score:3, Informative)
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: (Score:2)
Try using a displacement map to do a face and you'll notice that the nostrils are totally fudged up.
Re: (Score:2)
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: (Score:3, Interesting)
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.
Re: (Score:2)
8 years for cattle modeling? (Score:2)
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: (Score:2)
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
Why bother (Score:3, Funny)
Only if it makes the math easier (Score:2)
Favorite quote from my Mechanical Systems professor. I was surprised how much ME's use that in the real world.
Re: (Score:3, Insightful)
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 . . . (Score:5, Interesting)
. . . http://www.mndl.hu/works/fractalcow [www.mndl.hu]
Parent
Re: (Score:2)
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: (Score:2, Informative)
Re:Why bother (Score:4, Informative)
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?
Parent
Re: (Score:2)
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: (Score:2)
Nah, that's a bull.
Re:Why bother (Score:5, Funny)
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."
Parent
Re: (Score:2)
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!
Not normal maps? (Score:2)
Bump maps are so 20th century.
Misleading title (Score:4, Interesting)
Photosynth [photosynth.net] is far more interesting if you're excited by this concept.
Mr Santax (Score:4, Funny)
Umm.. maybe (Score:3)
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: (Score:2)
Re: (Score:2)
Re: (Score:3, Insightful)
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
This is Crazybump (Score:2, Interesting)
What about videos? (Score:2, Interesting)
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.
New Gilligan's Island (Score:2)
Now, if only voice reproduction and voice morphing technology was moving at the same pace as video.
Re: (Score:2)
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: (Score:2)
Getting closer... (Score:2)
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 comp
Go to Angkor Wat (Score:3, Interesting)
I'm posting this really late in the thread so maybe nobody will read it (or care) but...
If there is one place on earth that is crying out to see this technology used it is the KILOMETERS (really!) worth of intricate stone carvings at Angkor Wat (Cambodia). I've thought about borrowing (stealing?) a friend's $500,000 laser scanner to capture them but the 1) he (his institute really) probably wouldn't let me 2) the thugs who run Cambodia would probably not let me use it without me paying some extortionate amount. There really is no-where else on earth where you can see the results of thousands of man-years of skilled stone carvers. This priceless cultural heritage should be captured before pollutants like acid rain slowly erodes it or thieves literally dynamite it to pieces.
Now perhaps anyone with a good video camera, a steady hand, and a LOT of patience can get this done! Perhaps if this job is too large for any one individual to complete it could be done in sections and the individual video sequences shared over the internet. Anyway, I hope this software is modified to handle video (subject to certain restrictions such as shooting in progressive mode).
Re: (Score:2)
Re: (Score:2)
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 (Score:5, Informative)
Parent
Re: (Score:2)
Re:VERY, VERY (Score:4, Insightful)
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?
Parent
Re:VERY, VERY (Score:5, Funny)
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]
Parent
Re: (Score:3, Funny)
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: (Score:3, Funny)
An ASCII picture of a Penrose triangle. Never thought I'd live to see the day. Well done Sir.
Re: (Score:3, Interesting)
Re: (Score:2)
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 y
Slashdot prior art (Score:2)
You're right, we even read of that on... Slashdot [slashdot.org]!
Re: (Score:2)
"This guy has wasted his life."
Saith the foolish geek posting on Slashdot.
Pot, meet kettle.
MER does it [Re:VERY, VERY] (Score:2)
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: (Score:2)
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: (Score:3, Funny)
Re:Anyone care to explain (Score:4, Informative)
Bump mapping [wikipedia.org] is often used to add textures to otherwise flat surfaces. Basically, the bump map is a channel where the intensity of a pixel represents the height (rather than colour) of the pixel.
It's very similar to this toy [shinyshack.com], which I'm sure you've probably seen before. The bump map represents the 3D shape of the object being portrayed. (It does have certain limitations; since each pixel can only have one height, the bump map can't represent surfaces which fold over themselves... e.g. a bump map of your face would look like your face from the angle it was intended to be viewed from, but from other angles you'd notice that the nostrils were solid underneath.)
Once you've generated a bump map, you can use it to render a true 3D surface, calculating the shadows based on the bump map and the position of the light source.
Parent