Photosynth Demo 204
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.
I tried to WTFA (Score:2, Funny)
typical microsoft "innovation"
Re: (Score:2)
Re: (Score:2)
The video only looks cool because their demos are done because their source photos are carefully chosen.
They didnt send a n00b out to take the photos.
Re: (Score:3, Informative)
Re: (Score:3, Interesting)
Re: (Score:3, Interesting)
I shrugged. Can someone take my photos on Flikr and use them to create new content without my approval?
Re: (Score:2)
Re: (Score:2)
Re: (Score:2, Informative)
http://www.ted.com/index.php/talks/view/id/129 [ted.com] Click Here
mod parent -1 wrong (Score:1)
mod parent -1 moron (Score:1, Informative)
Re: (Score:2, Funny)
Re: (Score:2)
Re: (Score:2)
TED [ted.com] is definitely a site worth visiting away, as this presentation is probably among the less interesting ones you can watch there. More people should check it out.
Re: (Score:2)
(http://talsma.ca/)
that's the same crap ad-infested garbage hype video as the one on youtube.
--
The only maxim of a free government ought to be to trust no man living with power to endanger the public liberty.
The Software is AWSOME! However the delivery... (Score:5, Informative)
Autostitch licensee? (Score:3, Insightful)
Re: (Score:3, Informative)
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 [videosift.com], just amazing stuff.
Re: (Score:3, Insightful)
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."
Wow, another innovative product from Microsoft.
Re: (Score:3, Informative)
Windows only. (Score:2)
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...
Re: (Score:3, Interesting)
Re: (Score:2)
The research to find common elements in pictures and from that the location where the picture was taken was a joint project between Microsoft and University of Washington. That was not purchased from a 3rd party.
Re: (Score:2)
Yes, they funded this innovation by buying equity.
C'mon, learn how it works. It's the system you live in.
Re: (Score:2)
Re: (Score:3, Interesting)
Huh? (Score:3, Funny)
That appears to be syntactically tolerable English. Semantically, though, WTF?
Re: (Score:3, Funny)
Pretty pictures.
Re:Huh? (Score:5, Informative)
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>
Re:Huh? (Score:4, Interesting)
Re: (Score:2)
Re: (Score:2)
Last week I found MS's fully textured (though low-res) 3d model of new york on their mapping site http://maps.live.com/ [live.com] and thought that was very cool (it puts google earth's gray blocks that only go to 59th street to shame).
Isn't that just Microsoft Flight Simulator data?
Re: (Score:2)
It would be helpful if cameras had GPS location and direction metadata to give the software a starting point.
Re: (Score:2)
WTFV.
Re: (Score:3, Insightful)
Yeah, it's pretty decently cool, too. Personally, I thought the magazine and the car ad with highly detailed information "printed" really small was as interesting a concept at anything-- it looked like it might provide a reading experience that would make sense for an online magazine, and the small print bends the concept of your printable space in an interesting way. So long as there are sufficient hints that the tiny text was there, it would allow you to put a lot of information into a small "space".
Th
press release (Score:1, Flamebait)
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.
Re: (Score:2)
Re:press release (Score:4, Insightful)
Now that's a real summary! (Score:5, Funny)
Some impressive things (Score:5, Interesting)
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
Re: (Score:2, Insightful)
> fantastic.
Yeah, that's got to be running on a bog-standard Vista install, hasn't it. I agree with the guy - I can't think of a better way to read a newspaper than to pan around and zoom in on a huge monitor in my front room. And I can't wait to see what happens to this system when it's attacked by spammers creating fictional spaces. Whats to stop people from adding the world
Re: (Score:2)
what ads? (Score:2)
Re: (Score:2)
http://www.ted.com/index.php/talks/view/id/129 [ted.com]
I submitted this exact story about PhotoSynth and SeaDragon to Slashdot a few days ago and it was rejected. Boooo!
Re: (Score:2)
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.
Yeh - but now I'm scratching my head wondering how they do that.
Don't get me wrong, I'm blown away by the impressiveness of it, but I want to know (even roughly) how it's done. I can't for the life of me figure out how you can take random photos of the internet, throw them into some software, and have it churn out a 3d map based on nothing more than the photos.
Seriously, it's so awesome that I almost can't believe they really did it. I would love to even just get a vague idea of what they're doing to make
Re: (Score:2, Interesting)
Step 1) Get lots of photos of a given subject
Step 2) Process these photos and find "similar points"
Step 3) Start correlating points on separate photograps
With enough points in common on two or more photographs, you can begin to get an idea of the 3D relationship between the points, and also the cameras taking the photographs.
There are applications that allow you to do Step 2 manually (the clearest example of the process I found was http://www.3dphoto.dk/UK/technique-UK.htm [3dphoto.dk]), but Photosynth appear
One step forward! (Score:4, Interesting)
Re:One step forward! (Score:4, Interesting)
Every single paper I've seen from MS research is great. Well done!
(from someone developing computer vision on linux)
Re: (Score:2)
Seriously? It's the same in any industry. Just look at the 'concept' cars released by major car manufacturers - the actual cars made seldom have more than a glancing resemblance with those cars. Making a sweet prototype is not nearly the same as making something for mass consumption.
Re: (Score:2)
Re:One step forward! (Score:5, Informative)
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.)
The Humane Environment (Score:5, Interesting)
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.
Re: (Score:2, Informative)
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.
Savor it. (Score:2)
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.
Re: (Score:2)
Like it or not, Microsoft Research is doing very serious computer science, and has a lot of top people being allowed to really push the envelope.
Re: (Score:2)
http://research.microsoft.com/research/default.as
Microsoft does fund real research just like any other research lab.
Re: (Score:2)
It's great that the people who came up with a great idea are reaping the benefits. But as far as most slashdotters are concerned, MS is just going to patent the most basic ideas of the interfaces of the future to make sure no one will be able to sneak up on them again, a
Re: (Score:2)
While I've read that it doesn't work on Linux, the demo works fine on Firefox (but sadly not Opera). I realize that's not as good as it could be, but it's better than just IE...
Re: (Score:2)
It's here! Web 2.0 is HERE!!! (Score:5, Insightful)
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!
Re:It's here! Web 2.0 is HERE!!! (Score:4, Interesting)
I don't think that basic rasterizing engines are the limit. The limit is that the source data for all these pictures are tens or hundreds of gigabytes (and in the future, conceivably terabytes). Somewhere in the assembly and cross-correlation of all this data, they have to be generating LOD's (levels of detail) and dynamically loading / managing MIP-maps to keep the loaded dataset to a reasonable level. This is the hard part since "reasonable level" for loaded imageset size is probably currently a couple hundred megabytes or much less. You can probably load more data into RAM but try maintaining a 60FPS refresh with a gigabyte of textures - especially on a laptop or basic computer.
Once you've done this you can use a variety of display techniques... the main reason to use basic texture-mapping / flat rasterization is that sources are photos which are basically a pre-lit "flat" textures.
However, if you can generate a 3-D model and can separate lighting / color information (perhaps using combinations of day and night pictures or varying lighting from different photographs), it would be then possible to perform simple ray-tracing or other hybrid renderers -- think how cool it would look to have a dynamic artist's sketchpad with these images "penciled" in realtime. There are already high-frame-rate (near-realtime) ray tracing demos already out there for CELL and X86 that render moving images at a lower-res for higher-interactive frame rates and then when not-moving, render high-quality image stills that are quite impressive.
Re: (Score:2)
Photosynth + Views = ubercool (Score:2)
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.
Amazing Software, Lackluster Comments (Score:5, Insightful)
Re: (Score:2)
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".
"But look, you found the notice didn't you?"
"Yes," said Arthur, "yes I did. It was on display in the bottom of a locked filing cabinet stuck in a disused lavatory with a sign on the door saying Beware of the Leopard."
Covered on /. a year ago... (Score:4, Informative)
Just looking at that (Score:3, Interesting)
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!"
Re: (Score:2)
Re: (Score:2)
But hey, don't let the truth get in the way of an M$-bashing opportunity.
Why this will never be available ... (Score:2, Informative)
The whole thing is based on SIFT keypoints http://www.cs.ubc.ca/~lowe/keypoints/ [cs.ubc.ca] . These are very powerful and work indeed as shown in the video/demo. Check autopano-sift http://user.cs.tu-berlin.de/~nowozin/autopano-sift
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 SIF
Re: (Score:2)
Data aggregation (Score:4, Interesting)
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".
Re: (Score:3, Insightful)
Technology is a tool. It is great to use hammers to build houses. It is not great to use hammers to bludgeon people's skulls. In no way does thinking photosynth is fine imply that TIA is fine - the fact that they (may) require the same technology to be possible does not in any way make them morally equivalent.
Vast Desktop... (Score:5, Interesting)
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.
Re: (Score:2)
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.
I thought so too. This was a nice example of how you can handle lots of visual data via a limited screen, and one solution I'm very familiar with are virtual desktops. I couldn't stand using a computer without them, as you can easily focus on one task in one desktop. Windows and OS X in comparison look incredibly messy, as they attempt to present all of the computer's capabilities at once. I actually prefer a relatively small screen, and I've come to greatly appreciate the idea that computers let you wor
Official, Slashdot has become insane. (Score:2, Informative)
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/2007/06
Ya, PhotoSynth is a cool technology, but not exac
Nice but perhaps not as new (Score:2)
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 [graficaobscura.com] notebook. He calls it image merging via a projective warp [graficaobscura.com] and
Re:Does anyone have an actual video of the demo? (Score:4, Insightful)
Re: (Score:3, Informative)
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 advertisemen
Re: (Score:2, Funny)
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?
Re:Does anyone have an actual video of the demo? (Score:5, Informative)
Also there's microsoft's page [live.com], 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!)
mod parent up (Score:2)
This system was demoed a while ago, I think at siggraph. There are some videos on the original university of washington PhotoTourism page. [washington.edu]. Also here's a repost of the video on youTube. [youtube.com]
Thank you, that youTube link is exactly what I was looking for: A clear video demo of what this is, how it's used, with a nerd voiceover explaining what's going on.
No frills, no fuss, no slick intro telling me how I should feel about the damn thing, just info.
Re: (Score:3, Interesting)
Re: (Score:2)
The page also links to sample collections and a Photosynth Firefox plugin. [live.com]
Re:Does anyone have an actual video of the demo? (Score:5, Informative)
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 [live.com] today.
I did a video interview [onten.net] 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 [live.com] at Live Labs.)
We know you tried this at least once... (Score:4, Funny)
Re: (Score:2)
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.
Re: (Score:2)
linux & mac can try the old demo (Score:2, Interesting)
Re: (Score:2)
I'll have you know I also changed the word "often" to "awesome", but yeah, sorry about that.
Ah, I missed the word change. No need to apologize to me.
not flamebait (Score:2)
'cause that link is an annoying ad.
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 [slashdot.org] and this, from the same user in the same thread with the same insult, is redundant flamebait. [slashdot.org]
Re: (Score:3, Insightful)
Re:Interesting (Score:5, Funny)
Re: (Score:2)
You forgot:
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: (Score:3, Funny)
Re: (Score:3, Informative)
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 (Micros
Re: (Score:2)