Fotowoosh, a new service from Maryland-based startup Freewebs, will turn any image (preferably an outdoor image) into a 3D model. They went live on Friday. Examples of what the service can do are above (along with the original 2D images. A video is here which shows more examples.
The 3D image is constructed in Virtual Reality Modeling Language (VRML) format, meaning you currently need a VRML reader to see it (future browsers will likely build this functionality in). In a week or so, the company say, users will be able to upload a picture and have a 3D animated image returned to them in a Flash widget that can be embedded on any website.
When you upload an image to Fotowoosh, their software tears it apart and distinguishes the sky, ground and vertical elements within the photo, then cuts and folds it into a 3D model:
Our system automatically constructs simple “pop-up” 3D models, like those one would find in a children’s book, out of a single outdoor image. The system labels each region of an outdoor image as ground, vertical, or sky. Line segments fitted to the ground-vertical boundary in the image and an estime of the horizon’s position provide the necessary information to determine where to “cut” and “fold” in the image. The model is then popped up, and the image is texture mapped onto the model.
This is the creation of Derek Hoiem, a PhD candidate in Robotics at Carnegie Mellon University, who’s now working with the company. Additional information on the intellectual property behind Fotowoosh is here and here (these links auto-download a pdf and a powerpoint document).
Microsoft is working on something related to this in their Live Labs group called Photosynth (more information here). The product will construct a 3D model based on lots of photos of the same thing or general area from different angles.
Freewebs raised $11 million in venture capital in August 2006 from Columbia Capital and Novak Biddle. The company’s main product is a website building tool that draws 18 million or so visitors per month. Shervin Pishevar, the company’s president, say that Fotowoosh will be a standalone service, and they’ll also integrate it with offerings from partners as well as the Freewebs service itself.
Great find..I would like to implement this feature today. This has real estate industry written all over it.
oh that’s 3d thing is easy to make… All you need wireframe and image shaper to bend it. It’s like Computer Aiding Design program… I’ve seen it on GTA and game developers.
It’s not that new. I saw quake 3D.
After linking around… the sites
I found this… Hey mike why haven’t you cover this?
http://labs.live.com/deepfish/videos.aspx
Great find.
I like the idea a lot.
The technical implementation is good….but I was wondering what is the commercial use of this technology…. can some knowledgeable guys throw some light on this…
This is neat. Good work Derek!
Advice for fotowoosh… Since you got vc funding. Don’t grow too strong and too big. Why??!?!
Be careful with bully competitor… they will do harm.
There’s tons of playground bullies around web 2.0. People use GPL and give away their software…
GPL programmers fear of web 2.0 competition
It’s hardly new at all, just web’ifying a quite old technique, known as “photogrammetric modeling.”
The software ‘Facade’ was shown at SIGGRAPH back in 1996, and it inspired the consumer software Canoma.
Adobe acquired this 1997 program in 2000, and let it go extinct through lack of use.
Realviz has had the more powerful ImageModeler in their arsenal of 3D apps for at least as long.
It’s more about packaging and having a friendly user interface. Canoma and ImageModeler were okay, but the minute count (approx 15 mins for an average user to create a model) was what put people off I think.
Experienced 3D artists can create the same effect from polygon primitives and texture maps, so the main audience will probably be lay people, but ultimately it begs the question, “once you have the model, what then?” Maybe this startup has worked out an answer.
Great stuff, new or not. Real estate search via the web would certainly be impacted.
Hmmm.. this has significant potential.
In my opinion Yahoo should acquire them. I can easily see Yahoo using this technology along with all the images within Flickr to greatly enhance their Maps offering. Bear in mind that most Flickr photos have location information built in.
Let’s face it, Google and Microsoft maps kick ass. Its time Yahoo did something new. Also this mashup map will actually be using user generated content from the web. What could be more Web 2.0?
PS — Remember Flickr Explore feature. Using this technology and location data they can introduce 3D explore feature.
Mike, what do you think?
Abhishek
“future browsers will build this in ?”
Netscape aquired paper software in 1996 ! for there VRML browser.
This is one of those technologies that seems forever right around the corner.
VRML has been “right around the corner” for the past 10 years. If it was a website, it’s still have one of those “under construction” graphics on it.
All, thanks so much for the comments. Thi is Shervin Pishevar, President of Freewebs. Just want to address some of the questions about what our ideas are about the business side of Fotowoosh:
* we will widgetize this and let anyone and others websites publish and share these user generated 3D pictures virally everywhere. you will not have to use a VRML viewer to view your pictures once we fully launch.
* we will work with our widget advertising partners to explore advertising opportunities especially around the local angle. If you look at the 3rd picture example in the video you will notice a local store sign on the right with its lights on in the window. You could never notice that in the 2D version. What if that local business could have a link and more information available from the Fotowoosh version of the picture? It would be neat to then integrate this into Google Maps or MS Maps Live or Yahoo Maps and have user generated views of area on a map that are Fotowoosh transformed and explorable.
* we think real estate companies and for sale by owners will love showing off their properties and rooms using this on their sites.
There is more but I’ll stop here.
Cheers,
Shervin
check out my Freewebs site: http://www.shervin.com
I think that’s some nice work, well done.
It’d be interesting seeing what some of those ‘real’ Escher illusion photos would turn out like.
I fail to see how that is not useless. If they could make a product that allowed you to go all the way around and above the building, or go on all sides of the train for say 5 or 6 cars and not be really lossy, then I would be wowed.
3D is the future of the WEB - especially as 64-bit, and Hi-Speed DSL becomes more prevalent.
In about a decade, a 3D plug in will probably be as common as the Flash player or Java Applet is now.
thank you for sending your coment to use.
Thanks for taking out the video that starts playing automatically. I was even able to stop it from loading (or stop the video, for that matter).
It’s bad enough Snap is busy pre-loading data into my browser each time I visit here.
(A lot of us overseas visitors don’t have unlimited internet like in the US. Here in Oz, for example, they can get 5GB per month of downloads for the amazing price of AU$50.00)
/rant
Re: Reg ‘It’s hardly new at all’ & Nice ‘It’s not that new. I saw quake 3D’
If there is one thing I hate about web2.0 is that any id–t who thinks they are an expert gets to litter the internet with their useless comments. Did you people read the article. If you’re so knowledgable about the field maybe you should already know the background behind this or at least have been able to follow some links to go quickly inform yourselfs. Check this page out: http://www.cs.cmu.edu/~dhoiem/. The work behind this resulted in numerous cvpr, iccv and siggraph papers. These papers were peer reviewed (by real experts in the field) - part of the acceptance criteria was novelty. In fact this work won best paper at cvpr last year.
Too bad reg and nice weren’t asked to review the work - I imagine that review would have been someting like - ‘dude I think I saw something like this at GDC, yeah it totally rocked, yeah this math stuff in your paper I totally don’t get it but I heard from some guy who knows a lot of algebra and stuff that he’d thought he’d seen something like this already’
This is pretty cool and could see a lot of use for it!
This is quite good, I am a bit impressed.
it is cool. i think it can be more better,the baby’s heart is crzay.and i also have a idea.maybe somedays you can visit it.
This looks cool for web. But doesn’t look new to me. Even Microsft windows Media Center also has the photogallery which also has similar effects.
@Dip — I agree with you that this is not comparable to quake 3d.. at the same time you should note that from the very nature of that comment, the nuances are lost on the general populace at large. Indeed, quake can do a lot of what the above movies show, and has a level editor. You could also build a model of stuff in sketchup and fly your way around it (another thing that has nothing to do with figuring out perspective projection angles from photographs, but you get the picture - no pun intended). And the fact that someone asked about quake is relevant to the business model at large..which is that people see both as solving the same problem - 3d (or 2.5 d visualization).
There are many of these offerings on the market. If you go look at the real estate industry you will note there are people offering solutions that vary from a full laser scan of a room to get really accurate 3d readings, all the way to people doing panaromic stitching of photographs to build a flash/java movie.
I’m really surprised by the other trend — people seeing a cool demo, and stating that google or yahoo should buy these people. A cool demo has nothing to do with a good business model, or even whether the technology is solid..not making any statements regarding this particular technology, but rather with the trend in general.
This looks cool for web. But doesn’t look new to me. Even Microsft windows Media Center also has the photogallery which also has similar effects.
I have signed up for Beta Invitation. Soon will blog about the features.
I am really impressed about this new feature in web.
~ RaJ
http://www.suggestusability.com
I think most people here aren’t getting the point. Sure you can model 3D scenes using photographic textures in any number of software packages. We know.
The genius here is that the 3D scene generation is entirely automated. The software looks at a picture and determines where every pixel fits in the 3d space and renders it accordingly and it does this entirely by analyzing the image itself. In effect it is converting a 2d photograph into a three dimensions _without human intervention_.
Photo in.. three dimensional model out.. entirely automated!
This is unlike anything else currently available (at least to my knowledge). I wish people like the above negative commentators would really take the time to do some reading before blathering their idiotic comments all over TC.
“Even Microsoft windows Media Center also has the photogallery which also has similar effects”
Ummmm no.
“If they could make a product that allowed you to go all the way around and above the building, or go on all sides of the train for say 5 or 6 cars and not be really lossy, then I would be wowed”
I would be wowed too if this could be accomplished with a *single* input image but it’s impossible.
“oh that’s 3d thing is easy to make… All you need wireframe and image shaper to bend it. It’s like Computer Aiding Design program… I’ve seen it on GTA and game developers.”
No, it’s not at all like that. There is no modeling required.
Sigh.
They began with a strong sense of practicality “The company’s main product is a website building tool that draws 18 million or so visitors per month.” then ascertained $11 million in VC funds, but I’m failing to see the practical application of a 3D modeling app that transforms pictures into *somewhat* three dimensional models.
Also, this is VRML format…what does this have to do with innovation or web 2.0? Come on Tech Crunch, it’s not like you’re hard up for material.
wow. great. i’m gonna insert this tutorial in my website!
Kelly, It has a lot to do with innovation. Not sure what it has to do with web 2.0, but this ain’t a “web 2.0″ blog.
Photosynth is much more impressive, i saw a demo in seattle. Blows your mind away!
Makes me dizzy…
pr0xy k1ll3r, remember this is from 1 picture. big difference.
proxy - yeah, these are completely different products, for completely different things. Photosynth is very cool though.
michael’s reply to kelly is such classic über-pwnage…
“Kelly, It has a lot to do with innovation. Not sure what it has to do with web 2.0, but this ain’t a “web 2.0″ blog.”
Wow. Awesome find. Thanks for digging this, whoever posted it!
Wow!!! Very nice idea and technology. Clearly the commercial value is infinite.
I liked it better when it was called Canoma.
Slap bracelets.
Parachute pants.
I kiss you!!!!
I think this thing has fad written all over it, if it ever reaches some level of popularity among the masses. “Remember those pointless ‘3D’ pictures we made in 2007 and put on our sites? What the heck were we thinking?!”
Umm. Yeah. Install a plugin and then open a zip file for each sample? Not likely.
Call me when you get that flash widget working folks.
geoff, will do!
Looks good, useful for anyone who builds websites showing rooms - hotels for example
awesome, good idea
delicious.
Nice
That is cool How fast is it? I would love to know the price for this.
Shit… They are charging for that? I learnt how to do it with very little 3D experience on Cinema 4D in 30 an hour (and would probably take me now between 3-15 minutes, depending on how much time I waste reading digg in the meantime…)
Very Good development. Its effect would be felt in a wide range of fields.
@elmimmo –are not every good things come for a price?
Thats pretty freakin awesome!
http://www.bloggingwv.com
Ugh, seems half the people posting don’t even understand what the technology is, what it’s not, that it’s beta, and how impressive it really is.
Nice’s nonsensical Quake and GPL ramblings takes the cake though.
IMO, the killer application for this involves head-mounted displays that can project computer images into your frame of vision and a bunch of other image processing techniques that are just coming into maturity.
I’d build a game like this:
1. A camera on the glasses takes snapshots of your surroundings and using Fotowoosh-like algorithms builds a 3d representation of the area.
2. Create a Half-Life 2 (or whatever the latest 3d shooter is) map on-the-fly using the 3d data on the environment.
3. Now you need some more AI smarts to keep track of where you are in the 3d environment as you walk around the real environment.
4. Insert monsters and other baddies to shoot at. Only the bad guy character models would be rendered through the glasses. The rest of the game environment can be thought of as 3d models with invisible (but not transparent) skins on them.
5. Now you need some technology to translate a toy gun’s angle, etc, into game terms.
End result:
Put on these glasses, turn the game on, and hideous monsters and aliens will start coming at you from your real world environment: from around corners, behind trees, out of the water, through a window?
Best part is that since your graphics processor doesn’t need to render the environment (haven’t followed game programming for a while, but this is usually a large % of the polygons) you can either insert more bad guys or more detailed bad guy models.
Of course you’ll also need a pretty hefty processor to do all of the on-the-fly calculations to scan the environment. But I don’t see any reason they couldn’t fit this onto a mounted head display in the next 3-5 years.
I think once games like this come into reality, we’ll see two things:
1. Gamers will get in better shape (already seeing this with the Wii and Dance Dance).
2. No one would do anything else but play these games.
3. (BONUS) People will get freaked out at all of the kids running around with guns and try to ban these games. Every single shooting will be blamed on this game.
This is definitely the future of gaming. I thought about this a while back, but you have just said what I was trying to say. You should get a business grant and start working in this.
It is surprising that no-one has mentioned the obvious limitations of this technology. Objects are in 3D, then they are converted to 2D - information is lost! You can’t get it all back. Look up “optical illusions” in Wikipedia, for example Necker cube.
I dont want to sound like a pessimist overhere,
but I doubt how long this will appeal to common people out there. It would be fun giving couple of tries but after that how many people will want to convert every picture to 3D.
Of course this technology may find ways into scientific research institutes.
This has great applications for showing houses online. It’s hard to get a true spatial awareness of a room or lot without 3D - this could do the trick!
Wow now that is cool! And a neat name too
Am I the only one getting motion sickness from looking at these pictures? From the sounds of things, if this gets widely adopted, I might have to start taking some Gravol before browsing the internet.
I wish them luck, tools like this are often fun to play with but struggle to find good applications.
Another candidate for “they did this before, and possibly better” is Mok3, Inc. They have wonderful tools and won the DemoGod for 2003, got written up in Ny Times, USA Today, etc. They were lauded as the most impressive demo by many folks.
http://www.usatoday.com/tech/c.....side_x.htm
They even did some great work for the city of Boston to do 3D projections of the big dig. But i guess it never quite got traction as a general tool — looks like they have reconstituted into a 3D travel site.
http://travel.supertour.com
VRML lives! Done a bit VRML markup a couple of years ago.
This would be a nice feature in Adobe After Effects. You can do it already in After Effects, but you have to break the elements out into various layers and position them in 3d Space. This looks easier, but who knows what they do on their end.
I want this for my ‘curvy’ friends photos on Facebook
It’s certainly hugely impressive: I can understand why this might be useful for visualizing older photographs, but… surely it would be more practical to just, y’know, wander around your target location with a video camera, authentically capture the scene, and then compress and upload a Flash video of that?
If I could have that as a desktop background across both my monitors I think I could brag a little more.
Rock on, CMU!
thats cool…. a picture essentially worth a thousand books.
Nice trick for industries wanting to show a new perspective on a 2D image, but we all know the difference. Take your train photo and let my fly the camera under to see the back side of the wheels…. say there is brake trouble for example and you are doing a news story animation. A cute trick, but not 3D.
So just my 2cents - this is really impressive and super cool. Shervin kudos to you guys for taking a stab at something this complicated. obviously anyone versed in these matters realizes this is quite novel - they don’t use photogrammetric tools since this is done only from one point of view. i understand (read the papers Dip linked to at the CMU website) they use something dubbed geometrical contexting where they basically assume that every photo has a 3D model consisting of sky, flat ground surface and vertical planes. they then analayze the phto and define the various regions and then basically define the bending points and morph the image onto the “assumed” 3d model - Shervin was that close to correct?
Also i wonder if the process is indeed fully automated…i would assume that depending on the input image even the smartest algorithms could render silly results….if the Beta SW is client only and with no user intervention (read: they dont do any slash tech touchups in the server side) i would be even more impressed!!
at any rate one wonders what would be the mass appeal of this technology -
* Consumer level (Fliker)….well it seems that the main forte of the technology is well defined geometrical shapes. notice that the fine structure is lost (see trees and so on). Beyond that i assume that people will be distorted in this type of rendering (see the demo with the street and person standing on the left sidewalk)…and since most common photos people take and store have people in them this could be a big hindrance for wide spread sustained use.
* Marketing - definitely. super cool effect that is probabaly very well suited to a world where 3D cameras are not yet abound!!
* Real estate….again. big IF IMHO. as some people mentioned not only is fine detail lost here but there is very limited immersion effect and some distortion. Although this is indeed cool i am not sure what the added value will be over current solutions in this field like video tours, panoramas, flash and so on. there misght be a backlash against the lower preceived quality that these techniques yield (something like “no, no, dont worry the fireplace isn’t a trapzoid…oh and that black patch in the right corner is just a rendering articaft”. But i guess time will tell. obviously these are very talented guys and this is just preBeta.
*gaming - interesting indeed. i guess only the creators can say what kind system requirements rae needed (MEM and MIPS wise) and how far this is from OTF level.
Shervin - I wonder if you would care to comment? Especially on the human distortion issue.
Mike
very nice!!!
this is very very interesting
不错
sweet!!!
This thing is amazing. Wow. I wonder how they do this.
that is so cool
This is really cool
WOW!!!
Thank you for your site
I made with photoshop backgrounds for myspace or youtube and whatever
my backgrounds:http://tinyurl.com/6rbxmr
have a great day and thank you again!