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.
but I couldn't... 30 seconds of ads at the beginning, then the phrase "through an aquisition".
typical microsoft "innovation"
~/.sig: No such file or directory
That appears to be syntactically tolerable English. Semantically, though, WTF?
Can we get an editor who doesn't post/write press releases too? We're geeks, we know about blogs, you can't bullshit us with your PR so quit trying.
It's insulting when an article like this appears and SCREAMS "We were paid for it".
Either write like a human being or stop trying to impress us, because you can't do both.
I like muppets.
That is such a perfect name. I can't believe no one has thought of it before.
What I'm listening to now on Pandora...
that's the same crap ad-infested garbage hype video as the one on youtube.
~/.sig: No such file or directory
Then you closed the window about 10 seconds before the demo started. Keep watching.
Best Windows Freeware
The link that the GP posted was to the same video, but it splits the presentation into three parts (Advertisement, Enter Seadragon, The Photosynth Experience) that you can easily skip between. The good part starts at about 30 seconds into the clip.
Here is a better link to the video demo. Pretty Amazing stuff
http://www.ted.com/index.php/talks/view/id/129
I could only watch the video, cause apparently linux pictures aren't part of the collective consciousness. Still that's pretty fucking cool.
photosynth is already occupied by nature in hardware and in software, so i dont need anything m$ like with that name right now
clear case of prior art
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!)
Unlike the first set of posters I managed to get over my self importance and watched a couple of seconds of BMW ads to see the actual video.
I liked the initial viewing of large quantity of hi-res images and the smooth zoom. The aggregation of many thousand flickr images of the Notre Dame (including one of a poster on a wall) into a 3-D image was fantastic.
C
In the interests of openness, would you mind publishing these calculations of yours? I'm sure we'd like to see your quantification of the open-source development process, particularly for software as complex as this evidently is. Thanks.
At least now someone at Microsoft seems to know _what_ to buy, this is some pretty amazing technology. I just hope that someday it will be available to other OS'es too.
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.
This zoom-ability of the first part has a lot in common with the ideas behind Jef Raskin's The Humane Environment http://en.wikipedia.org/wiki/Archy/.
The second part, however, shows marvellous stuff. Especially if what I think he did, was search for patterns in images, and compare those for unique objects to collect a library of images of a single object.
This guy and supposedly his group shouldn't work for Microsoft in my opinion, but would perhaps feel more at home in a fundamental science laboratory. But I think my opinion on this is slightly partial.
B.
Every experiment which ends in a big bang is a good experiment.
A few days ago? Try a few months ago. Microsoft was demoing this at O'Reilly's Web2.0 Summit in SanFran last November. Very cool, not very new.
No frills, no fuss, no slick intro telling me how I should feel about the damn thing, just info.
You can't take the sky from me...
It was (and I thought it was obvious that it was) a joke, I am aware that there won't be an alternative for a long time.
However I was making the point that Microsoft shouldn't try and be competitive on all fronts, as they simply aren't that good.
At least if they make a good operating system the users who will never switch to Linux will still have access to a good operating system.
Most people I know wouldn't consider switching to Linux (I do know a guy who downloaded a liveCD, but overall he didn't feel he could easily make the switch) but most people I know have no problem using open-source programs such as Firefox, Thunderbird and GIMP for everyday stuff...
It would appear that Microsoft could make a great operating system without having to develop IE and a bunch of other needless tools, and not only would they have a better OS and therefore be more loved, they'd save money developing IE and stuff.
This system was demoed a while ago, I think at siggraph 2006. There are some videos on the original university of washington "PhotoTourism" research page. Also here's a repost of the same video on that page on youTube.
Also there's microsoft's photosynth page, which has the demo (it's been up for months). 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. It could be used by a single person, but it's definitely well suited to large collections such as flickr. 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 to thinks its awesome (even non-slashdot readers!).
Didn't rtfa, but I recall seeing some video of this a while back. Imagine in an ideal world, with all the photographs everyone had taken taken at every concievable angle of just about every place on the planet, this could, if not put Google Maps' street view to shame, gain a following ready to pooh-pooh on Google's offering. Overlay on Google Earth and SketchUp (or whatever MS' competing product,) for extra awesomeness.
Granted not everyone's photos were taken at the same time, but you could group them together by time period to create a reasonable reconstruction. On top of that, since you have now have a time element you could in addition to doing a fly/walk through of a location, turn the clock back. For example (at the risk of sensitive pick,) explore around the World Trade Center property before & during construction, and before & after 9/11.
The QOTD seems very appropriate for this article: Any sufficiently advanced technology is indistinguishable from a rigged demo.
Life is wet, then you dry.
You can stitch pictures of your home but we can see thru your window ! (streetview) But seriously though kewl piece of technology. Sundru
This guy and ... his group shouldn't work for Microsoft
Someone else pointed out that the actual work was done outside of M$, but I agree that it's a shame they were bought up. Expect this to be crushed instead of landing on your desk.
Friends don't help friends install M$ junk.
All those next-stage, new-wave, super-hyped ideas that generated enough excitement to get a survivable user-base just kind of passed me by, because they only ever seemed to be minor amplifications of what we already had. But this... this is something totally new. And utterly, utterly incredible!
I'm so excited by this it's making me feel sick! TECHNOLOGY! INTERWEB! I take it all back - forgive me for my lack of faith! I LOVE YOU!
And by the way, that "content only limited by how many pixels are on the screen" idea has been a long time coming, and I'm deeply happy that someone's solved it. I could never understand why we use raster-imaging for computer games because it's a squillion times quicker than ray-tracing, but nobody had applied the same idea to other applications. Now I feel justified in wondering, and I'm so pleased with the result!
Meta will eat itself
Diversification? Xerox realized they couldn't rely on photocopiers forever and created PARC. (Unfortunately for them it took others to truly deliver PARC's work to the public at large.)
Windows and Office brings in buttloads of cash, but it can't hurt to do develop ideas in other areas, especially when they have the cash to throw at it (or small upstarts.) Some elements of that work might even work their way back into MS' flagship products as new features, (or if you prefer, bloat.)
This software is absolutely amazing, especially when you consider the programmatic side of this. People bashing this without actually watching the video AND playing with the operating demo are really missing out. You don't have to like it but at least have a reason that shows some form of intelligence. Not just "the intro was poorly done".
Or did you repost this exact message 15 minutes later for fun?
Curious how things go around here.
Friends don't help friends install M$ junk.
The page also links to sample collections and a Photosynth Firefox plugin.
What I'm listening to now on Pandora...
Right here.
Animoog.org
Will this turn into a viable service (web service or not) anytime soon?
:-)
I read this has enormous space requirements *and* computations associated with it.
Sure, it's amazing once all image data has been calculated and matched against each other, but I have a hard time seeing this being available for end users soon, unless they just happen to be sitting on a tasty... Beowulf cluster?
Beware: In C++, your friends can see your privates!
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.
To be perfectly clear here, this technology is not new. Here's a group from Carnegie Mellon university doing something similar a year ago. There are many companies that have algorithms that can generate three dimensional data from 2 dimensional pictures. What Microsoft has done here is take the existing concept, put a proprietary 3D interface around it and tie it all into photographs obtained from the internet. A nice evolution of the state of the art, but hardly revolutionary.
youtube videos don't have ads, but your not the first one to mention this in this thread. Weird. Were you on the other site? Why would microsoft have ads in their own techdemo?
I'll just use my special getting high powers one more time...
rather fabulous demo, I realize that that would tie in beautifully with the surface computing MS showed last week (which was lovely as a tech demo with little immediate use). :)
Vista is 'nice' but it's just a progression of what we already know - these tech demos give me a big warm fuzzy futuristic feeling inside
If nothing else it shows that MS is innovating again (at last) - Ball's back with Apple and Google now - "Make me more impressed!"
You can't take the sky from me...
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.
Near the end of his presentation, the guy sums up the technology as taking all of these separate images from various sources on the net and figuring out how they all interlink to present a larger, more coherent picture. He got applause.
My first thought was about the U.S. government's "total information awareness" project, where they're trying to take lots of separate pieces of info (which are already available to law enforcement) and interlinking them all together to provide a more coherent picture... but most people consider that to be evil.
Granted, the government isn't doing it with vacation photos, but the idea, of finding pieces of data that are related and finding out *how* they're related, is the same. The difference in people's reaction to it, I can only attribute to the fact that people see the photosynth guy as good, and the government as evil. But I don't agree that the goodness or evilness of an action is solely determined by the goodness or evilness of who's doing it. The U.S. gov't tries this and fails. It expects that it can invade foreign countries and install friendly governments and torture people because it's "the good guys", yet the soviet union did those same things during the cold war and we admonished them for it because they were "the bad guys".
So, where am I going with this rant? My point is this: You can't blame somebody for connecting the dots. In fact, that seems to be one of the things that we, as humans, are particularly good at. So, if you think that this photosynth thing is fine, then I think you've got to grant that the TIA project is fine. Now, you could argue that some particular bits of information shouldn't be available, but the piecing it together to form a more coherent picture... I can't come up with an argument against it that I consider defensible. Sure, it makes me uncomfortable, but that's not an "argument".
Sounds like an application of autostitch. The downloadable demo version is pretty neat and fun to play with, if you have overlapping scenery photos, for example.
Have you read my blog lately?
I was looking at the demo, and one of the pictures has Stephen Hawking in it.
Actually, as I looked at the demo, I couldn't help feeling like all that virtual space was looking like a damn nice desktop environment. Nevermind the part of the demo with a flat-on scrolly-zoomy desktop, as nice as that would be (Seems obvious in a way too... And wouldn't it be nice if Leopard had that instead of "Spaces" ?). But imagine the notion of opening up an application and instead of just popping up a new window it creates a new space - within the desktop virtual space - and brings you into it. You can always pull back and move around to another window or workspace, but while in it you'd be totally immersed.
I dunno, I just like the notion of immersive environments, especially for conceptual learning. I think we're going to see a prevalence of this kind of interface in the near future.
-- thinkyhead software and media
I have to say, there is something funny about Microsoft providing a Firefox plugin. Very cool in the geek sense, but kinda weird.
-Billco, Fnarg.com
I don't like it.
Kind of like fucking a dirty hooker.
I installed it, then had trouble uninstalling it (it might have been in Unistall but I couldn't see it so I deleted manually)
I don't like executables being linked into Firefox.
Once a plugin is there, its executable and available to any page wanting to use it.
Anything additional is a potential expliotable hole.
liqbase
Day 300: There's another project in Sourceforge that isn't really doing much. and no one really remembers it except it's creator. The projects main page links to a domain squater.
"...what I'm going to show you...is some new technology that we brought to Microsoft as part of an acquisition..."
Fuck Microsoft. Fuck them and their can't-beat-em-then-buy-em business model. Fuck their complete lack of innovation, and fuck the douchebags who sell out to them. This Gary Oldman-looking motherfucker just got assimilated and all he can say is thank you. Newsflash, Commissioner Gordon: You know all the blood, sweat, and tears that you personally put into this project? All the birthdays you missed and the bridges you burned and the times you could have been getting laid? Microsoft gets to call it their own now. You're a footnote, the answer to a trivia question now, like Seattle Computer Products or Spyglass, Inc.
Unethical business practices? Monopoly? Clueless donkeys who lap this shit up year after year? It doesn't matter. The fact is that Microsoft has sufficiently integrated itself into any and all aspects of technology that nothing-- not Google, not Linux, not whatever the fuck the bloggers can come up with-- will make it go away.
Seriously, it's too late to do anything about it. Accept it as a fact of life or go build a shack in the mountains of Montana.The neutrality of this sig is disputed.
You miserable cunt.
I can't send on music I get from Microsoft (DRM) to friends, but they can use my photos to beter their online content? Gosh, that does not seem fair. Can I buy a "Microsoft Rocks!" tee shirt for $100 too?
I hate slashdot
How the fuck is that offtopic?
Not only is this discussing the content of the links from the summary, but the comment above and below are modded up.
Did someone give Microsoft's marketing department modpoints or something?
You can't take the sky from me...
"I think because as a part of microsoft, the technology will be used to bolster the market share of internet explorer, rather than be available to everyone regardless of their OS or browser. The current photosynth demo is an activeX plugin."
You people and your narrow minded bigotry.
And now in Firefox
It's been great for us to watch your comments, suggestion and ideas around Photosynth. As you know, this is a long term project and the team continues to make progress on a daily basis to add more functionality to the underlying technology. After we released the technology preview in November we saw a number of requests for a version that would work in Firefox. Live Labs is committed to making our technologies available to the widest possible audience, and today we're happy to announce the availability of the Photosynth Firefox plugin. We know that you are waiting for the day when you will be able to create your own collections, and that will happen, but in the meantime look for more beautiful new examples of Photosynth in action over the coming months.
Adam Sheppard
Group Product Manager
Live Labs | Microsoft
I watched the video and I must say, as a professional photographer that is the coolest fucking photgraphic thin I have ever seen. But I still say microsoft wants it both ways. Use our stuff for free and to have us pay for theirs.
I hate slashdot
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.)
I closed the window when it got to "this has never been shown to the public" or some such piece of hype. Read the FAQ: Flamebait refers to comments whose sole purpose is to insult and enrage. If someone is not-so-subtly picking a fight (racial insults are a dead giveaway), it's Flamebait.
This is flamebait and this, from the same user in the same thread with the same insult, is redundant flamebait.
You can't take the sky from me...
That's hot. Glad to hear the photos were presented as is (except for the ones that were removed) and that the computer vision works well enough to get lots of good alignment through feature detection. Seeing photosynth at work for the BBC should be great (I showed photosynth to a friend at the New York Times and it sounds like they'll be jealous).
First, it's spelled "douchebag$"
Secondly, despite popular belief, MS bashing has no instrinsic value other than somehow increasing the "Insightful" property of /. postings (go figure).
Finally, innovators have the right to sell their technology to anyone they want, even the highest bidder.
Error:
PhotoSynth was previewed and available months and months ago, like a year almost.
6 /06/windows-live-photodoom-alpha-silverlight-power s-new-microsoft-live-labs-project.aspx
The real news story today is about using Silverlight technology in a new Live project.
Today's MS story was about "Windows Live PhotoZoom". A set of features managing photos using Silverlight using some of the original PhotoSynth technologies.
http://www.liveside.net/blogs/main/archive/2007/0
Ya, PhotoSynth is a cool technology, but not exactly new, at least not today.
We know that SlashDot as the 'Faux' news of technology, but at least get the article at least '1%' correct, and skip the links with insane ads not related. People on here actually think they are MS ads.
University of British Columbia: "Hello."
Bill Gates: "Hi, this is Bill Gates. We'd like to work with, help fund, and give deep discounts to your University's computer science department, in exchange for a patent usage agreement."
University of British Columbia: "Sure!" And if they don't want to license - they are shameful, wasteful trolls. They're no different from the large corporations who abuse patents - and they deserve to be stripped of all claims.
As an aside, what business does a Canadian university have holding US patents that they do not intend to use?
Gee. Talk about selective reading. Why don't you post the entire thing?
"This demo software is provided for research purposes only. A license must be obtained from the University of British Columbia for any commercial applications. The sofware is protected under a US patent as listed below. This demo software is a research implementation, while the licensed software has been further optimized for speed and to provide a range of other capabilities. See the LICENSE file provided with the demo software."[Emphasis mine]
Well, there's a demo on Microsoft's website. I don't know if that counts as "commercial".
Wow... found a picture with stephen hawking sitting and talking to some people in the Piazza San Marco collection. Anyone else spot that?
I enjoyed it. Reminds me in some ways of Photomesa.* Now I'm just waiting to see the base principle applied to sound.
*"Enemy of the State" as well.
... was that it was a BMW ad that he was zooming in on,
as well as having BMW either side of the demo.
Someone obviously colluded _before_ this demo was even presented.
Don't know about everyone else, but I feel manipulated...
--
mefster can't remember what his sig says
I confess I had to watch the video without sound in my office but if as people are saying the image warping is automated, then it sounds very much like work done by Paul Haeberli of Silicon Graphics and posted in his Grafica Obscura notebook. He calls it image merging via a projective warp and works IIRC by lining up patterns in a collection of images automatically. It took like an hour to do this on something probably as powerful as a top of the line PC though so perhaps the tech in the video is not really doing the same thing.
It should be noted that he posts a bibliography too (below). I don't see SIGGRAPH but he does have the following. Not to diminish (too far) the developer's work but these things aren't created in a vaccuum you know. I do agree with other posts though, this is stunning and I'd like to have my OS built around this!
Incidentally there is also a creative commons attribtued video about drm that involves panning around a giant page with embedded videos in it. Also past work by famed computer graphic artist Daizaburo Harada did some things like that too, though of course about 100 times more beautiful and with music if I remember. Something also going on with morphing images of eyebrows and nether regions until your sensory apparatus is irretrievably hacked...
Clearly then, you'd be the one to ask... What happens when you enter "Jessica Alba" into Flickr and use photosynth?
Life, the Universe, and Everything... in my image.
And what makes you think that MS didn't buy alicense to SIFT like so many other companies?
there's a demo that is OS agnostic (java applet) on the washington Phototourism page.
If it could link pictures of the insides of buildings to the outsides of the same buildings? Maybe you'd have to deliberately shoot through the windows if the building has them to give it context. (Use flash to give it both inside and outside detail). I'm thinking it would be nice to see the inside of the temple I worship at in 3D space (2D isn't the same as being there. Maybe 3D wouldn't do it either). It would be great for that info to be related to where the temple is.
I'd imagine at the moment the software would try to union all Hindu temples in existence. You'd get a few million different views of each deity taken in different temples overlaid onto each other.
Sounds exiting research though!
Listening to the voice of the commenter I could'nt help to notice that in some passages it is exacly the same as Microsoft SAM speech engine! Maybe a strange compression artefact (or more unlikely a playback performance :D). Also if you look behind the presenter in some scenes it is visible a green OLPC with the antenna raised! (it is on the left looking from the public)
The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.
Deja Vu fooled Washington once. shame on you, fool me twice, shame on me. This is no computerized 3d modeling, what they did is they are able to fold time space into seeing the pass at another location.
You forgot:
Quote
Windows XP SP2 and Vista Only
The Photosynth technology preview runs only on Windows XP SP2 and Windows Vista.
If you feel you've reached this message in error, you can try anyway.
Unquote
Typical...
IANAL but write like a drunk one.
This is where we find out that all myspace pictures were taken in the same bathroom... and in 3D!
If girls liked guys that were interested in them for their brains, they'd date zombies.
All I can say is the presentation didn't look that polished. The dude doing the dog and pony show looked like a bonafide, neck-beard sporting, t-shirt wearing geek. The overly rapid pacing of his speech and lack of inflection on what he was talking about indicates that he probably wasn't a professional marketroid. He also appeared to be intimately familiar with the application which is a giveaway.
I've been imagining, and trying to figure out how to do, a combination of the two.
Have a truck drive around photographing everything, and run the photos into software to generate the 3D model. Now we see - in practically the same week - both parts of that in place. Just string the two together, throw in public-accessable photos, crunch a few terabytes, and we'll have one of the coolest applications EVAR.
Can we get a "-1 Wrong" moderation option?
Lowe (the prof behind the whole thing) does not want to sell/licence it to M$. He does not need the money and the U cannot do anything about it.
Since you worked on it, would you happen to know where I could find some more detailed technical information about it (e.g. what algorithms were used, how it was implemented, etc.)? I'm a student working on a computer vision project, and I'm very interested in it.
"[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz
This page at University of Washington has a link to the original SIGGRAPH paper (PDF) which describes in rather general terms the mechansim by which Photo Tourism (the first shot at Photosynth) works. That paper (and its references should get you started.)