Strecha, ChristophPylvanainen, TimoFua, Pascal2010-04-122010-04-122010-04-12201010.1109/CVPR.2010.5540184https://infoscience.epfl.ch/handle/20.500.14299/49316Recent 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.bundle adjustmentlarge scale reconstructionDynamic and Scalable Large Scale Image Reconstructiontext::conference output::conference proceedings::conference paper