Dynamic and Scalable Large Scale Image Reconstruction

Recent approaches to reconstructing city-sized areas from large image collections usually process them all at once and only produce disconnected descriptions of image subsets, which typically correspond to major landmarks. In contrast, we propose a framework that lets us take advantage of the available meta-data to build a single, consistent description from these potentially disconnected descriptions. Furthermore, this description can be incrementally updated and enriched as new images become avail- able. We demonstrate the power of our approach by building large-scale reconstructions using images of Lausanne and Prague.


Published in:
Proceedings of 23rd IEEE Conference on Computer Vision and Pattern Recognition
Presented at:
23rd IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, U.S.A, June 13-19, 2010
Year:
2010
Keywords:
Laboratories:




 Record created 2010-04-12, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)