From Single Image Query to Detailed 3D Reconstruction

Johannes L. Schonberger, Filip Radenovic, Ondrej Chum, Jan-Michael Frahm

CVPR 2015

doi:10.1109/CVPR.2015.7299148 /cvpr/2015/schonberger2015cvpr-single/

Abstract

Structure-from-Motion for unordered image collections has significantly advanced in scale over the last decade. This impressive progress can be in part attributed to the introduction of efficient retrieval methods for those systems. While this boosts scalability, it also limits the amount of detail that the large-scale reconstruction systems are able to produce. In this paper, we propose a joint reconstruction and retrieval system that maintains the scalability of large-scale Structure-from-Motion systems while also recovering the often lost ability of reconstructing fine details of the scene. We demonstrate our proposed method on a large-scale dataset of 7.4 million images downloaded from the Internet.

PDF CVPR Semantic Scholar

Cite

Text

Schonberger et al. "From Single Image Query to Detailed 3D Reconstruction." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299148

Markdown

[Schonberger et al. "From Single Image Query to Detailed 3D Reconstruction." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/schonberger2015cvpr-single/) doi:10.1109/CVPR.2015.7299148

BibTeX

@inproceedings{schonberger2015cvpr-single,
  title     = {{From Single Image Query to Detailed 3D Reconstruction}},
  author    = {Schonberger, Johannes L. and Radenovic, Filip and Chum, Ondrej and Frahm, Jan-Michael},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299148},
  url       = {https://mlanthology.org/cvpr/2015/schonberger2015cvpr-single/}
}