Slashdot Mirror
3D Virtual Reconstructions From Microsoft
Lord Satri writes "New around the corner, Microsoft Live Labs' Photosynth, will 'take a large collection of photos of a place or object, analyzes them for similarities, and displays them in a reconstructed 3-Dimensional space.' There's a demonstrational video and a 'smart photos' example page. From the site Very Spatial: 'The word is that Photosynth will be available for free, at least at first, but no word yet on an exact release date.' I must admit, seems like Photosynth may offer interesting features with an clean interface. This tool will directly compete with Stitcher, and to some extent, Google SketchUp. The virtual world reconstruction tools market is getting crowded, and competition is good. Microsoft doesn't yet have software to tie a photo library with Windows Live Local (Google does), but don't be surprised if it comes to life."
Yes, there is this software: http://user.cs.tu-berlin.de/~nowozin/autopano-sift /
It is GPL'ed but the problem is that it is using a patented algorithm (SIFT features) so it is not free to use in commercial applications without paying I guess.
pooyak.com
REAL VIZ has been doing this stuff for years. They even have a few movies under their belt where their software has been used. http://www.realviz.com/
I use Hugin Panorama Tools. I think it works really well, though I don't have a lot of experience with other stitchers. It can do panorama stitching, and also correct for barrel distortion and such.
This isn't really pixel zooming, it "zooms" by determining which of the pictures of the scene it has is closest to the view selected by the user, and switching to that one, rather than zooming in on a specific image. So if you, for example, select to view the head of a statue from a picture of that statue, it looks for a picture of the head of statue, then views that. It's pretty neat.
If you watch the linked video (which is definitely interesting and the main example demoed is of a square containing many bystanders, by the way) you will see that the software blends photos together. Presumably it does a lot of color matching and softening of hard seams. When the camera moves from picture to picture in the virtual space, people and cars sometimes fade in/out, but it's not jarring and is somewhat hidden in the shift in aspect.
I know you asked about an Open source stitcher, but there's also Autostitch to have a look at. It's Windows-only, but from what I can tell, their demo version has no time limit, and it does an impressive job with braindead simplicity : select pictures, click go.
I agree with Erich Schubert's blog post (http://blog.drinsama.de/erich/en/2006073102-micro soft-vapourware, found via http://planet.debian.org/) that it's more vapour than some E3 "rendered in-game" footage. Citing the UWash Photo Tour (http://phototour.cs.washington.edu/) whose technology ultimately makes up PhotoSynth, the processing power required is of the scale of two weeks to place 597 of 2635 images using a 3.4 GHz P4. I doubt that too many home computers will have the grunt to do that on a reasonable time-scale before the end of the decade. I expect it will be a serviceon Microsoft Live, where you submit the pictures and use a viewer.
There was a long discussion of pano tools, both free and commercial, over at dpchallenge.com a while back. That link is to the first page where the discussion starts, way down at the bottom. From that thread, it would appear that, while a major PITA to install and learn to use, Hugin produces results that are typically at least as good as most of the major commercial tools and are far better than many of them.
If you're a real-estate agent, it's not really that big of an investment to buy a Kaidan 360 lens. It only takes a few seconds to take a picture with, and you only have to snap one picture. Their software builds a quicktime VR of the environment. In my opinion, a quicktime VR gives a better presentation of an environment than what was seen in the MS software anyway. The only benefit to the MS stuff is that it will let you zoom in on particular features you photographed more close-up, where I believe that Quicktime VR is the same resolution all around.
The MS stuff is still supposed to do all this auto matching-up of different people's photos and stuff, but for a simple VR tour of some location, the Kaidan lens and a digital camera seems like a superior way to go. Of course, if you're not a professional and only want to make one of these every now and then, you might want to use the MS stuff instead of having to invest in a new lens.
Can anyone tell me how to set my sig on Slashdot?
It doesn't just let you zoom in (which, by the way, Quicktime VR can do too); it lets you look at the scene from any arbitrary perspective. It's the difference between just standing still and looking around in Quake and actually running around the level.
"[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz
Their video is also MUCH better. Much more impressive, they show some very cool features Microsoft did not. Still, both videos only show the User Interface. Not the calculation of the dataset. It is however no secret that Microsoft PhotoSynth is basically this with a different UI. Or maybe completely the same. (Notice that the Microsoft name is both present on the PhotoTour homepage and the paper for SigGRAPH).
Do also read the SigGRAPH paper. This is the actually tech part. http://phototour.cs.washington.edu/Photo_Tourism.
Some interesting facts you'll find there:
- They used a 3.4 GHz computer.
- The Notre Dame example took two weeks to compute.
- only 597 of the 2635 images were used, the rest was discarded.
This definitely isn't of much use to "home" users. You'll need a semi-professional photographer to cover the whole location. If there are some bigger holes in the imagery, you'll probably not get a useful result. If the images don't overlap, how is the software supposed to calculate their relative position?Debian GNU/Linux - apt-get into it.