New Technology

[Gerritt]

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."

 

 

http://ai.stanford.edu/~asaxena/reconstruction3d/

 

Seems the actual test section is down for maintenance at the moment... but look to it when it is back up and test it on your photos!

 

Gerritt.

[evster]

Wow, that looks pretty cool. I'm definitely going to give that a try once it is back up.

[fatherof3]

looks great,cant wait to try it,thanks for the link

[fatherof3]

The link seems to work now,uploaded a pic but am #105 for getting it processed.