Slashdot Mirror
Stanford's New Website Converts Your Photos to 3D
An anonymous reader writes to tell us that Stanford has a new website that not only shows you how cool their new 3-d modeling system is, but actually allows you to give it a try with your own photos. The system can take a 2-d still image and estimate a detailed 3-d structure which you can navigate. "For each small homogeneous patch in the image, we use a Markov Random Field (MRF) to infer a set of "plane parameters" that capture both the 3-d location and 3-d orientation of the patch. The MRF, trained via supervised learning, models both image depth cues as well as the relationships between different parts of the image. Other than assuming that the environment is made up of a number of small planes, our model makes no explicit assumptions about the structure of the scene; this enables the algorithm to capture much more detailed 3-d structure than does prior art (such as Saxena et al., 2005, Delage et al., 2005, and Hoiem et el., 2005), and also give a much richer experience in the 3-d flythroughs created using image-based rendering, even for scenes with significant non-vertical structure."
Aaaaaand it's already slashdotted.
Wow. That was fast.
Official Heretic from the "Church of Global Warming". Proven right thanks to whistle blowers. AGW = Flat Earth Theory
Wow, can you imagine how cool this would be with respect to video games? Drop in some photos, crank up the customized first person shooter, and zoooom! You could even take photos or shots from movies and do the same thing (e.g., using Star Wars stills).
How to Download YouTube Videos
Could this type of technology be used for robots to allow them to identify what the 3d layout of the world around them is? Seems like a pretty powerful tool in that area.
The sound of 1 million slashdotters instantiating a Markov Random Field at Stanford.
Bright idea to post the url on the front page.
I tried it - it converts your face into a Mars flyby.
Take the cheese to sickbay, the doctor should see it as soon as possible - B'Elanna Torres, "Learning Curve"
Im guessing the link isn't responding...
Probably because 10,000 slashdotters are testing the software, with various images containing grits.
Dammit, and all this time I've been decrying the impossible magical 3-d photo processing in Blade Runner! Curse my skepticism!
--Tedb0t
Limina.Log
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
It is not slashdotted. The server crashed after I gave it an image of the impossible triangle.
whatcouldpossiblygowrohwaitnevermind
While I know you're all Microsoft haters, bear with me for a minute. This sounds a lot like this Photosynth demonstration. The relevant part of the video starts at about 3:50, but the whole video is really interesting and I would suggest watching it.
granted, radar doesn't work so great for transparent surfaces to get the depth cue from -behind- that surface, while lidar gets a little iffy if it's -too- transparent to get the depth cue of that very surface. Combination of both - voila.
This would be sweet if they took all the imagery from google maps/streets and build out little virtual cities with no headed pedestrians and 5 legged dogs.
3D pr0n finally a reality! Awww, those sissies at Standford are too weak for the slashdot effect.....and I had some pixxx all lined up for 3D-izing.....
Hey, you think your house is cool?
Several years ago I worked at a german university where recognizing of human faces was researched. We also did 3D reconstruction of faces, which was useful for training some algorithms. Although the technique is very different, 3D reconstruction from 2D images is not that new. Some examples can still be seen here: link
Escher must be laughing in his Grave.
"Teach a man to build a fire, and he's warm for a day. Set a man on fire and he's warm for the rest of his life."
Since both the processing engine and the article are hosted on the same server, I can't even read about it. Anyone got a mirror to some sample input/output?
(No goatse renderings, please)
I only post comments when someone on the internet is wrong.
nt
I'm sorry to say that us geeks have been usurped by young hipsters in the website-disabling stakes. This site has not been slashdotted, it has been YouTubed. Someone at Stanford has been uploading videos of this to YouTube and inviting the plebs to go to their site before us. How ungrateful. The swines. Harumph.
HAL.
Got them moderator blues I blieve I walk out the do', With these mod-points I been gettin', I 'most never post no mo'
The porn industry would like to thank Stanford University for their breakthrough research.
Somehow along the way I made a bad choice in life and now must live with 0 Karma.
You do that. I hope you fall in.
... 3(r)D pst!11 .__________. /| /__________/ |
:(
/
/ / |
/ / |
| | z |
| O O | |
| \______/ | /
| | /
|___________|/
almost
A bit more DYI but cool.
Belief is the currency of delusion.
Other than assuming that the environment is made up of a number of small planes, our model makes no explicit assumptions about the structure of the scene;
Darn. My photos tend to be mostly of helicopters and boats.
Someone try to upload a mobius strip. I want to see whats on the other side.
be raster anyway. Spatial data would simply make more sense even if you were creating a flat print (as long as you have the sensor/processing/memory power).
Quack, quack.
The 3D site is still down. In the mean time you can use: http://simpsonizeme.com/
the Internet Boobies Data Base
You're kidding - right???
A quick search on youtube revealed this video which seems to be of the software in question.
The summary mentions prior work by Hoiem at CMU (slashdotted here), a video of which can be also seen on Youtube.
I'm not sure I'm very impressed by the Stanford videos. In the few examples of non-vertical surfaces, you can see quite a few artifacts.
anyone got a mirror to the 3d demonstration ? (if one exists)
killserverswithme
Has anyone tried anything by M.C. Escher? His stuff already blows minds in 2d. Or the site itself, did anyone mirror it?
Has anyone got any examples of before and afters, just so we can get an idea of what it does? Infact did anyone even get to use the demo before everyone saw the article and googled images for a Danni Ashe photo?
Wow, can you imagine how cool this would be with respect to video games?
It's getting there to an extent. The newest game using an ID engine, Enemy Territory: Quake Wars has an SDK where map-makers can load data from Google Earth to create terrain for their map.
I'm excited because I design skate parks and I frequently try to mimic popular real-world skate spots. A tool like this could allow me to import a photo of a plaza in Barcelona and get it into my CAD application without everything being guestimates. It won't be accurate, but things will be correct relative to one another and I can nail them down by hand.
Seth
$5 / month hosted VPS on linux = awesome!
This makes me wonder if it would be possible to convert the image to 3d, make a rendering, then convert the rendering again, from a different angle. If repeated, you could theoretically look 'behind' objects, to places that weren't visible in the original image. I assume you would just get black, but it would be interesting to try.
I was going to have a amazingly funny and clever sig, but I forgot, and failed miserably.
As the sever appears to be melted, does anyone have information on the supervised learning method used? SVM? ANN? Inquiring minds wish to know.
Cheers!
Cue Manga artists invasion in 3... 2... banzai!
#
# You may specify the path to the FastCGI crash log (a log of unhandled
# exceptions which forced the FastCGI instance to exit, great for debugging)
# and the number of requests to process before running garbage collection.
#
# By default, the FastCGI crash log is RAILS_ROOT/log/fastcgi.crash.log
# and the GC period is nil (turned off). A reasonable number of requests
# could range from 10-100 depending on the memory footprint of your app.
#
# Example:
# # Default log path, normal GC behavior.
# RailsFCGIHandler.process!
#
# # Default log path, 50 requests between GC.
# RailsFCGIHandler.process! nil, 50
#
# # Custom log path, normal GC behavior.
# RailsFCGIHandler.process! '/var/log/myapp_fcgi_crash.log'
#
require File.dirname(__FILE__) + "/../config/environment"
require 'fcgi_handler'
RailsFCGIHandler.process!
They must have a sexy error mesasge system too. I refreshed the page three times and I saw three different pages!
What would happen if you were to feed some hand-drawn images to this thing? I don't mean paintings as such, line-art. Anime. That sort of stuff.
This site http://www.photo-to-3d.com/ has been around for a while. And they also let you try it for free.
I wish I could mod you up to "President".
How can I get the 3D data generated from my uploaded 2D image into KML format, so I can upload that into Google Earth? Some VRML to KML converter?
--
make install -not war
Mind you, not even the Borg could handle that.
There is no sig.
Anyone remember canoma? It did something similar to this years ago. I don't know much about it because by the time I heard about it, Adobe had already bought it and killed it. Thanks again big software. =) -g
Too bad it's "down for maintainance." I'd like to have put a pic of some chick with her ass in the air in there. :p
I wonder what happens if you stick a 9-tailed fox in there?!