Modeling People and Places With Internet Photo Collections 27
CowboyRobot writes "Two researchers have created a system that aggregates thousands of photos from around the Web and integrates them into single images. One application is creating maps by taking the GPS coordinates of photos taken from a collection. Another is creating 3D models of historical buildings by automatically pasting together tourists' photos taken from different angles. 'The challenge is that online data sets are largely unstructured and thus require sophisticated algorithms that can organize and extract meaning from noisy data. In our case, this involves developing automated techniques that can find patterns across millions of images.'"
creating 3D models of historical buildings (Score:4, Insightful)
>Another is creating 3D models of historical buildings by automatically pasting together tourists' photos taken from different angles.
I remember seeing a Microsoft (?) thing that did that YEARS ago. Years and years and years ago.
What happened to that?
Re:creating 3D models of historical buildings (Score:5, Informative)
Re: (Score:2)
Actually, the original work seems to be stemming from what is now the Bundler project. A fork (so to speak) became phototourism and photosynth. But Slashdotters probably prefer Bundler
http://phototour.cs.washington.edu/bundler/ [washington.edu]
Re:creating 3D models of historical buildings (Score:5, Informative)
Noah Snavely is credited in both places, and this article cites "continuing research" into an "emerging field". The 2008 "Photo Tourism" project was turned into PhotoSynth, but the other stuff seems new.
http://research.microsoft.com/en-us/um/redmond/groups/ivm/phototours/ [microsoft.com]
Re:creating 3D models of historical buildings (Score:5, Informative)
He's also released a good portion of the underlying algorithms (though not the actual tools) in the open-source bundler [washington.edu] library, which is quite helpful in terms of having a base to build other applications on, or to do research in this area.
Re: (Score:2)
posting to cancel moderation error.
Re: (Score:1)
>> Noah Snavely
Wasn't that the villain in the last Harry Potter movie?
Re: (Score:2)
Me too. I remember one example/sample involving the Pantheon.
Next step (Score:2)
Yup and this is the logical next step.
Once you have spatially organised a bunch of photos (what was done in Microsoft's Photosynth tech demo), the next logical step is to use them to create 3D reconstructions.
The researcher (and apparently at least one of them is the same) now build 3D point clouds out of the photos.
Now someone should sell/license the technology to google.
By combining photo albums with the data they already have from street view, they could build some really nice 3D models of towns building
Re: (Score:1)
12 year series of papers at siggraph (Score:5, Informative)
The first paper I recall was constructing a 3D model of the Berkeley campus from individual snapshots.
Google Street View uses a variant of this technology.
MicroSoft and NASA joined forces after the Columbia accident to generate a view of the Space Shuttle from hundreds of closeup pictures taken from the space station.
I saw a paper by architects constructing the entire interior of an office building from a large series of snapshots. Its considered more accurate for building engineers than the architectural drawings.
Re: (Score:1)
Can you give a reference to the Architecture paper? I'm researching around this at the moment.
Photosynth (Score:2)
Photosynth generated point clouds in 3D and let you view each image from its original vantage point, but now seems to be concentrating on panorama stitching. This project seems to have taken a more interesting direction.
DIY (Score:2)
Or just take a bunch of photos yourself and upload them to Autodesk's 123d catch [123dapp.com] and get a 3d model back. It'll stitch together a scene and make a mesh (or a mess, depending on your photo quality) of it.
It's obvious what to do... (Score:1)
2. Feed Streetview images into a 123dcatch instance on it.
3. Run some surface fractal texturing code to apply a "creative" element while cleaning up the surface dirt, pixellation, etc. and reducing file size.
5. Get the mechanical turk to describe the objects for a few cents each.
6. Auction commercial-use licenses to Garmin,
TomTom, etc.
7. Profit $$$
Gaming twist (Score:4, Interesting)
Would be cool to recreate the whole real world using this technique. Build an MMO around it. Would be a cool way to crowd source out your game's mapping work.
Re: (Score:3)
You might be interested in PhotoCity [photocitygame.com], then (a research project at the same university PhotoSynth came from).
Re: (Score:1)
I am working on starting PhotoCity up again!! In the mean time, I've been making a 3D modeling tool to turn point clouds (from PhotoCity or the Kinect or anything else) into polygonal models. Now I plan to join the pieces together!
Here's the link to the point cloud modeling tool, PointCraft: http://www.photocitygame.com/pointcraft/ [photocitygame.com]
So... (Score:1)