Stanford's New Website Converts Your Photos to 3D 156
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."
For those that can't get in (Score:5, Funny)
Re:Slashdotted (Score:5, Funny)
Blade Runner anyone? (Score:5, Funny)
--Tedb0t
Re:Slashdotted (Score:5, Funny)
Inside Story (Score:5, Funny)
!Slashdotted (Score:5, Funny)
Re:Slashdotted (Score:5, Funny)
Re:!Slashdotted (Score:5, Funny)
Re:Slashdotted (Score:5, Funny)
Google's next toy (Score:4, Funny)
Re:Slashdotted (Score:4, Funny)
Hell, you need a reference? I've got a few gigs of references here for ya...
Re:Slashdotted (Score:3, Funny)
Example input/output, anyone? (Score:3, Funny)
(No goatse renderings, please)
Re:Not so new (Score:2, Funny)
Sorry, couldn't resist... uh-oh there goes my karma!
Re:Slashdotted (Score:1, Funny)
The server is even giving ICMP replies.
The webserver service hosting image processing software on the other hand...
went *POOF*
Tracing the path to make3d.stanford.edu
make3d.stanford.edu CNAME ai.stanford.edu
ai.stanford.edu A 171.64.68.10
1 10.0.1.13 (10.0.1.13) 0.131 ms 0.096 ms 0.047 ms
2 unknown.xeex.net (216.151.129.45) 0.605 ms 0.572 ms 0.734 ms
3 eq-exch.bb-peer01.cook.il.ena.net (206.223.119.116) 12.525 ms 7.000 ms 7.878 ms
4 137.164.129.2 (137.164.129.2) 59.882 ms 51.876 ms 51.860 ms
5 te4-1--160.tr01-plalca01.transitrail.net (137.164.129.34) 69.218 ms 69.343 ms 69.157 ms
6 calren-trcust.plalca01.transitrail.net (137.164.131.254) 73.582 ms 76.500 ms 78.923 ms
7 dc-stan--svl-dc1-ge.cenic.net (137.164.23.38) 76.226 ms 70.215 ms 70.236 ms
8 bbra-rtr.Stanford.EDU (171.64.1.134) 70.670 ms 70.382 ms 73.852 ms
9 * * *
10 ai.Stanford.EDU (171.64.68.10) 72.485 ms 75.918 ms 77.823 ms
seems limited (Score:5, Funny)
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.
Re:Slashdotted (Score:5, Funny)
Brian.
Re:Slashdotted (Score:1, Funny)
Re:It's not slashdotted. (Score:5, Funny)
Re:It's not slashdotted. (Score:5, Funny)