Dynamic and Scalable Large Scale Image Reconstruction
Abstract
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.
Cite
Text
Strecha et al. "Dynamic and Scalable Large Scale Image Reconstruction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540184Markdown
[Strecha et al. "Dynamic and Scalable Large Scale Image Reconstruction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/strecha2010cvpr-dynamic/) doi:10.1109/CVPR.2010.5540184BibTeX
@inproceedings{strecha2010cvpr-dynamic,
title = {{Dynamic and Scalable Large Scale Image Reconstruction}},
author = {Strecha, Christoph and Pylvänäinen, Timo and Fua, Pascal},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {406-413},
doi = {10.1109/CVPR.2010.5540184},
url = {https://mlanthology.org/cvpr/2010/strecha2010cvpr-dynamic/}
}