Efficient Structure from Motion by Graph Optimization
Michal Havlena, Akihiko Torii, and Tomas Pajdla
In case you do not have a VRML viewer and plugin, the one suitable for your environment can be found at: http://cic.nist.gov/vrml/vbdetect.html
Octaga Player (win, mac & linux): http://www.octaga.com/joomla/index.php?option=com_content&task=view&id=17&Itemid=40
'Castle image set'
Two largest partial 3D models reconstructed from image set Castle after 6 hours of computation (see Figure 6) together with sample input images:
|
|
| Right part of the St.Vitus Cathedral and other buildings in the square. |
|
|
| Entrance to the Prague Castle. |
'Vienna image set'
Two largest partial 3D models reconstructed from image set Vienna after 6 hours of computation (see Figure 7) together with sample input images:
|
|
| Rear part of the St.Stephan Cathedral. |
History of growing and merging of the largest partial 3D model after 12 hours of computation:
|
|
| Front part of the St.Stephan Cathedral. |
| hrs |
Twelve atomic 3D models were grown and merged into the final partial 3D model in 12 hours (click to enlarge): |
| 12 |
| 11 |
| 10 |
| 9 |
| 8 |
| 7 |
| 6 |
| 5 |
| 4 |
| 3 |
| 2 |
| 1 |
|
|
