Slashdot Mirror
Photosynth Demo
A couple of days ago Microsoft labs released a demo of their new Photosynth software on the web. Photosynth allows the aggregation of social picture networks (a la Flickr) into a completed image in addition to allowing a level of depth to image browsing previously unavailable. There is also a very impressive video of the demo available.
Better Link to the video demo.
http://www.ted.com/index.php/talks/view/id/129 Click Here
This lets you take all sorts of pictures of your room, and will automatically assemble them into a 3D environment. It will assemble your photos to look like an RPG, instead of a slideshow.
Using the example in the video...there are hundreds of online collections of people's photos of Notre Dame cathedral. Each photo is of a different part of it, from a slightly different angle.
This software takes all those different photos and assembles them into a 3D representation of Notre Dame cathedral, where you can look at any of the individual photos.
In addition, if someone identifies one of the saints in a statue on the cathedral, when you take a photo of it and your photo is added to the collection with the software, your photo will also have that saint identified--thereby enhancing the data contained in your photo.
- RG>
Hey pal, this isn't a pleasantforest, so don't waste my time with pleasantries!
This system was demoed a while ago, I think at siggraph. There are some videos on the original university of washington PhotoTourism page.. Also here's a repost of the video on youTube.
Also there's microsoft's page, which has the demo (I don't think that's new either). It seems to have some longer videos
Non-newness and marketing hype aside, this software is frickin' awesome. It lets you view and tag photos organized in a 3D environment that reflects where the photos were taken. It should be particularly useful once cameras have GPS built in.
I imagine the reason the software is still in the demo phase is because it's very difficult to take a large number of photos and reliably figure out where they were all taken from. For the demo purposes, Microsoft probably hand corrected a lot of the placements. Even so, everyone I've shown this too thinks its often (even non-slashdot readers!)
I decided wade through the hype/ads/blah, and came across a really cool piece of software. It takes thousands of flickr images stitches them into a 3-dimensional mosaic, all just through software. No special on-site 3d imaging hardware, just a program compiling everyday images of something. It does this through some very advanced image recognition. If you can brave the ads, it IS worth it.
The project was demonstrated on the Research Channel at the beginning of the year.
Microsoft bought out a company that had written the non 3D part of Photosynth and student(s) at the University of Washington wrote the rest if I remember correctly. At the time they didn't work for Microsoft.
Right here.
Animoog.org
The people responsible for creating the intro (TED) are just the people responsible for giving the presenter a forum to share their ideas/technologies, don't let it color your impression of the rest presentation or the technology itself too much. The same brief advertisement is used across all the videos hosted on the TED web site, for all speakers, some of whom include Al Gore, Bill Clinton, Richard Dawkins, Bono, Peter Gabriel, Jane Goodall, Ray Kurzweil, Sir Martin Rees, Michael Shermer and Craig Venter and in that context the intro isn't as over the top as it may at first seem, if you think TED is just all about showcasing new technological toys.
No, the demo is not rigged (and it's about 11 months old).
t / for a real application using them.
The whole thing is based on SIFT keypoints http://www.cs.ubc.ca/~lowe/keypoints/ . These are very powerful and work indeed as shown in the video/demo. Check autopano-sift http://user.cs.tu-berlin.de/~nowozin/autopano-sif
There is only a little problem, M$ cannot use SIFT commercially. The licence says "for research purposes only" and the US Patent 6,711,293, Asignee: The University of British Columbia protects SIFT.
No, it's far more advanced than that, as its recognition is able to match objects that are not directly from the same set of photos, or even all photos, some can be diagrams or drawings for example.
The part that blew me away is the SeaDragon technology behind the image/information scaling portion of things... now that is just incredible... check out a talk/demo at TED on March of 2007 by Blaise Aguera y Arcas of Microsoft, just amazing stuff.
You must not have seen the whole thing. The cathedral was assembled from images available from the internet taken by hundreds of different people and cameras.
This sig is exactly seventy characters long and a real waste of space!
I was one of thee engineers that worked on the first release Photosynth. It's a great team, and it was a super fun project.
I can tell you that we did not tweak any camera positions by hand. The only real "editing" we did was to eliminate pictures that just didn't correlate well, generally because they didn't have enough feature points in common with the rest of the photos. We didn't tweak any camera positions, but the camera positions (i.e. the locations of the orange camera frusta when you have frusta turned on) are a best estimate, which is subject to some error. Same goes for the projection planes.
What's great about Photosynth is that from the perspective of anyone outside the computer vision community, it appears to be magic. Enough so that lots of the blogosphere was convinced that we somehow "authored" the 3D point clouds. Nope. It's more or less an automatic (albeit somewhat prolonged) process. The hard work is done as a big preproceess, then the client consumes largely precomputed data.
It'll be cool to see Photosynth in action in BBC's upcoming How We Built Britain piece that was announced on Live Labs today.
I did a video interview about Photosynth a while back which is targeted at a non-technical audience but still might be of interest. (And I wrote the music for the original video at Live Labs.)
Microsoft didn't buy Photosynth. It bought Seadragon. The Photosynth client is indeed built on Seadragon's client, but the idea behind Photosynth (which was a joint University of Washington/Microsoft Research project called PhotoTourism) significantly predated the Seadragon acquisition, and there was a working client. When Microsoft decided to reimplement the client as a technology preview, that's when the Seadragon team and client came into the picture.
That said, Seadragon's technology is great. It's a fantastically smooth way to browse arbitrarily large images or collections of images, and it was a good acquisition indeed.
(I was on engineer on the Photosynth team.)
Dude, did you watch the video? The acquisition the guy mentioned was the first part - the zoom in and out and pan around lots of images. That was the "meh" part.
The cool part... the part where they constructed a 3D model of Notre Dame by using only photos from Flickr, well the Photosynth page says where that came from: "Photosynth is a collaboration between Microsoft and the University of Washington based on the groundbreaking research of Noah Snavely (UW), Steve Seitz (UW), and Richard Szeliski (Microsoft Research)."
The Online Slang Dictionary